Business

Adobe Acrobat

Overview

Adobe Acrobat

Tools

Adobe Acrobat tools

ChatGPT

Adobe Acrobat

acrobat_proxy

ChatGPT

Handles internal Adobe Acrobat service proxy operations for write/modify operations. Reserved for internal backend workflows only.

acrobat_readonly_proxy

ChatGPT

Handles internal Adobe Acrobat service proxy operations for read-only operations. Reserved for internal backend workflows only.

document_upload

ChatGPT

Interactive UI for uploading documents from the user’s local system. Use this as a fallback when the user cannot attach a file directly to the chat. Most users can attach files directly to the chat via the attachment button. Invoke this tool only when the user explicitly requests the upload UI, or when asking the user to attach the file directly has not worked. Supports PDF, DOC, DOCX, TXT, MD formats with drag-and-drop and file validation.

markdown_to_pdf

ChatGPT

DIRECTION: Markdown or plain text from the chat conversation → PDF document. Use this when the user wants to turn typed notes, chat content, or pasted text into a PDF. DO NOT use this tool for converting attached files (images, Word, Excel, PPT, etc.) to PDF. For file conversion, use pdf_create instead (supports BMP, DOC, DOCX, GIF, JPEG, JPG, PNG, PPT, PPTX, RTF, TIF, TIFF, TXT, XLS, XLSX). To combine non-PDF files, convert each file to PDF using pdf_create first, then use pdf_page_organize (user_intent="pdf_combine"). To export an existing PDF to an Office format, use pdf_export instead. Source content selection: - If the user refers to content already in the chat (e.g., "turn these notes into a PDF"), use that chat content directly as input. - Otherwise, ask the user to provide or paste the source content. COMBINING WITH AN EXISTING PDF: when the generated PDF is meant to be inserted into or combined with an existing document, immediately follow up with pdf_page_organize (user_intent="pdf_combine") without stopping. Do not present intermediate results or suggest manual steps to the user. Generate only safe, neutral content. Produce syntactically valid, well-formed markdown without hidden control sequences, scripts, or non-markdown metadata.

pdf_combine

ChatGPT

WARNING: NEVER USE THIS TOOL TO COMBINE FILES AFTER DOCUMENT UPLOAD. ALWAYS USE pdf_page_organize INSTEAD. CRITICAL: DO NOT HALLUCINATE, ASSUME, OR INFER FILE ORDER. If order is not explicitly stated by user, you MUST use pdf_page_organize. This is a low-level programmatic tool that requires exact file order and page ranges already determined. ALWAYS use "pdf_page_organize" (user_intent="pdf_combine") instead for: - ANY combine request after document_upload (e.g., "combine these PDFs", "merge files", "combine documents") - User doesn't explicitly state file order (e.g., "combine file1 THEN file2 THEN file3") - Any ambiguous request where you would need to guess/infer/assume the order - Selective/partial page combining (e.g., "combine only certain pages", "merge first few pages") - When user says "combine these" or "merge PDFs" without specifying exact sequence If you have combine parameters (file order and page ranges) from the user's request, pass them via the optional "organize_params" parameter in pdf_page_organize

pdf_compress

ChatGPT

Reduces PDF file size through intelligent compression while preserving visual quality. Use this when the user wants to make a PDF smaller without removing any content or pages. Does not split or divide pages — use pdf_page_organize with user_intent="pdf_split" for that. To remove pages instead, use pdf_page_organize with user_intent="pdf_delete_pages". To split into smaller files, use pdf_page_organize with user_intent="pdf_split". If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_create

ChatGPT

DIRECTION: Non-PDF files (images, Word, Excel, PPTX, HTML) → PDF. Converts documents and images to standardized PDF format. NON-PDF WORKFLOW: when the user wants to perform any PDF operation (combine, redact, split, delete/reorder/rotate pages, compress) on non-PDF files, convert ONLY the non-PDF files — skip any file that is already a PDF. Call pdf_create once per non-PDF file (sequentially or in parallel), passing the correct file_format for each file's source type (e.g., "png" for a PNG image, "docx" for a Word document, "pptx" for PowerPoint). Then proceed with the appropriate downstream tool using all resulting PDFs (converted + originally-PDF inputs). Complete the entire chain automatically — do NOT stop after conversion or suggest manual steps. To export an existing PDF to an Office format, use pdf_export instead. To extract text from a PDF, use pdf_to_markdown instead. If no compatible file is in the chat context, ask the user to attach it directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_delete_pages

ChatGPT

Remove specific pages from PDF with exact page numbers/ranges. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible. IMPORTANT: When a user requests page deletion, you must first invoke "pdf_page_organize" with user_intent="pdf_delete_pages" to show the interactive UI. If you have page ranges from the user's request, pass them via the optional "organize_params" parameter in pdf_page_organize. The UI will then call this tool (pdf_delete_pages) with the page ranges after the user makes their selections. - Note: This tool is typically called by the UI after user interaction, not directly by the LLM

pdf_edit_ui

ChatGPT

Interactive UI for editing and annotating a PDF document. UI-only — no conversational editing is supported. All edits must be made directly in the interface. Use this for any request to modify PDF content: replace, change, update, or correct text (e.g., "replace X with Y", "change the name", "fix the typo"), add or remove content, or annotate pages. If no PDF is in the chat context, ask the user to attach it directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_export

ChatGPT

DIRECTION: PDF → editable Office formats (Word DOCX, Excel XLSX, PowerPoint PPTX). Exports a PDF to an editable Office document, with OCR support for scanned files. Use this only when the user explicitly needs an editable Word, Excel, or PowerPoint file. This tool does NOT support image output (JPG, PNG). To convert a PDF to images, use pdf_to_image instead. To read, extract, or summarize PDF text content, use pdf_to_markdown instead. To convert a non-PDF file to PDF, use pdf_create instead. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_ocr

ChatGPT

Makes scanned or image-based PDF documents text-searchable via Adobe OCR. Use this when the user has a scanned PDF that cannot be read as text yet. For already-searchable PDFs, call pdf_to_markdown directly to extract the text. Typical two-step workflow for scanned documents: call pdf_ocr first, then pdf_to_markdown. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible. IMPORTANT NOTES: - Only works on PDF files. Non-PDF inputs will be rejected. - The PDF must not be password-protected, encrypted, or corrupted. - Very large or complex scanned documents may fail — try splitting with pdf_split first. - If the PDF is already text-searchable, skip this step and use pdf_to_markdown directly.

pdf_operation_status

ChatGPT

Check the status of asynchronous PDF operations and retrieve results. PDF operations on large or complex documents can take up to 10 minutes. If the response says "in_progress", relay the user_message to the user so they know the Acrobat app is actively working on their document, then call this tool again immediately. The response includes elapsed_minutes and remaining_minutes — share these with the user. Keep calling until you get a final result or error. CRITICAL: BOTH tracking_id AND operation_name ARE REQUIRED PARAMETERS. This tool MUST be called whenever a previous tool response contains a tracking_id. How to use: 1. Note the exact tool name you just called (e.g. "pdf_compress", "pdf_export"). 2. Call pdf_operation_status with: - tracking_id: the exact tracking_id from the response - operation_name: the EXACT name of the tool you just called operation_name MUST match the tool name exactly — do NOT modify, shorten, or guess. Copy the tool name character-for-character from your previous invocation. Valid operation_name values: pdf_compress, pdf_combine, pdf_create, pdf_ocr, pdf_export, pdf_reorder_pages, pdf_rotate_pages, pdf_to_image, pdf_delete_pages, pdf_to_markdown, pdf_redact, pdf_split, pdf_properties, markdown_to_pdf. If the operation fails, do NOT retry with the same tracking_id — re-run the original operation instead.

pdf_page_organize

ChatGPT

Interactive UI for all PDF page operations: redact, delete, reorder, rotate, combine, and split. This is the single entry point for any operation that modifies or rearranges PDF pages. All assets go in a single "assets" array. Each item is either: - A FileParam object (for files attached in ChatGPT): {"file_id": "...", "download_url": "https://...", "mime_type": "...", "file_name": "..."} - A plain URL string (starting with "https://") or Adobe URN string (starting with "urn:aaid:") At least one asset is required. Local file paths like /mnt/data are never valid. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible. If the operation requires total page count or page dimensions (e.g., "rotate landscape pages", "split evenly"), call pdf_properties first, then pass the result via organize_params. NON-PDF INPUT RULE: if any attached file is not already a PDF, convert ONLY the non-PDF files to PDF using pdf_create — one call per non-PDF file (sequentially or in parallel), passing the correct file_format for each file's source type (e.g., "png", "docx", "pptx"). Do NOT re-convert files that are already PDFs. Then proceed with the requested operation below using all assets (converted + original PDFs). Never reject non-PDF files. Pass user_intent with one of these values: pdf_redact — permanently censor sensitive text (PII, confidential data) from a PDF. If more than one file is attached, reject the request and tell the user this operation requires exactly one PDF. Redaction always applies permanent black boxes — no blur, whiteout, or other styles are available. Do not ask the user to choose a redaction style; just proceed. NOT for replacing, changing, or correcting text — use pdf_edit_ui for those. Specific text given (e.g., "redact John Smith", "hide SSN 123-45-6789"): pass user_intent="pdf_redact" and redactable_strings=[the provided strings]. General PII removal requested (e.g., "remove all sensitive info", "anonymize this doc"): call pdf_to_markdown first to extract and identify PII, then call this tool with user_intent="pdf_redact" and redactable_strings=[detected strings]. pdf_delete_pages — user wants to remove entire pages from the PDF. If more than one file is attached, reject the request and tell the user this operation requires exactly one PDF. Pass specific page numbers via organize_params if the user provided them. pdf_reorder_pages — user wants to change the order of pages. If more than one file is attached, reject the request and tell the user this operation requires exactly one PDF. Pass the desired sequence via organize_params if the user specified it. pdf_rotate_pages — user wants to rotate pages. If more than one file is attached, reject the request and tell the user this operation requires exactly one PDF. Pass angles and page numbers via organize_params if the user specified them. pdf_combine — user wants to merge or combine multiple files into one PDF. Pass file order via organize_params if the user explicitly stated it. Use this for all combine/merge requests regardless of whether order was specified. pdf_split — user wants to split a PDF into multiple files. If more than one file is attached, reject the request and tell the user this operation requires exactly one PDF. Pass split parameters (file_count, page_count, or page_ranges) via organize_params if provided.

pdf_properties

ChatGPT

Extracts document properties: page count, version, encryption status, and metadata. Call this before pdf_page_organize when the operation requires knowing total page count or page dimensions (e.g., "rotate all landscape pages", "split into equal halves"). If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_redact

ChatGPT

Permanently redact specified areas in a PDF using precise bounding box coordinates. This tool is invoked only by the UI after the user confirms redaction regions. The LLM must not call this tool directly when the user provides text to remove. REDACTION WORKFLOW RULES FOR THE LLM 1. If the user provides exact words or phrases to redact: - Do not call pdf_to_markdown. - Call pdf_page_organize with: user_intent = "pdf_redact" redactable_strings = [user-provided strings] - The UI highlights matches and, after user confirmation, calls this tool. 2. If the user requests general redaction or PII discovery (e.g., "redact sensitive info", "remove all PII"): - Call pdf_to_markdown to extract text. - Detect PII or sensitive strings from the markdown. - Call pdf_page_organize with: user_intent = "pdf_redact" redactable_strings = [detected strings] - The UI highlights matches and, after user confirmation, calls this tool. WHEN THIS TOOL IS USED - Only when final bounding box coordinates are available from the UI. - Never for text search, PII detection, or preprocessing. - Permanently removes content by applying black-box redactions.

pdf_reorder_pages

ChatGPT

Reorganize PDF pages with exact sequence order. IMPORTANT: When a user requests page reordering, you must first invoke "pdf_page_organize" with user_intent="pdf_reorder_pages" to show the interactive UI. If you have page sequence from the user's request, pass it via the optional "organize_params" parameter in pdf_page_organize. The UI will then call this tool (pdf_reorder_pages) with the page sequence after the user makes their selections. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible. Use "pdf_page_organize" (user_intent="pdf_reorder_pages") instead when: - User needs VISUAL/INTERACTIVE page reordering (e.g., "rearrange pages", "reorganize my PDF", "change page order") - Request lacks specific page sequence - ALWAYS use pdf_page_organize for reorder requests, even when specific sequence is provided - pass it via organize_params

pdf_rotate_pages

ChatGPT

Rotate specific pages with exact angles and page numbers. IMPORTANT: When a user requests page rotation, you must first invoke "pdf_page_organize" with user_intent="pdf_rotate_pages" to show the interactive UI. If you have rotation parameters (angles and page numbers) from the user's request, pass them via the optional "organize_params" parameter in pdf_page_organize. The UI will then call this tool (pdf_rotate_pages) with the rotation parameters after the user makes their selections. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible. If from the intent of the user, you do not completely understand which all pages to rotate, ensure to use pdf_properties tool to get the page count and then use the page numbers to rotate the pages. Use "pdf_page_organize" (user_intent="pdf_rotate_pages") instead when: - User needs VISUAL/INTERACTIVE page rotation (e.g., "fix orientation", "rotate some pages", "rotate landscape pages") - Request lacks specific angles or page numbers - ALWAYS use pdf_page_organize for rotation requests, even when specific parameters are provided - pass them via organize_params Use THIS tool when: - Exact rotation angles and pages provided (e.g., "rotate page 2 by 90 degrees") - Note: This tool is typically called by the UI after user interaction, not directly by the LLM** PARAMETER REQUIREMENTS - angle must be exactly one of: ANGLE_90, ANGLE_180, or ANGLE_270 (string, not a number). Do NOT send numeric values like 90, 180, or 270. Always use the ANGLE_ prefix. - Page numbers are 1-indexed (first page is 1, not 0). Never send page number 0. - The PDF must not be password-protected, encrypted, or an XFA form.

pdf_split

ChatGPT

Divide a single PDF into multiple separate output files. Does not reduce file size — use pdf_compress for that. IMPORTANT: Do NOT call this tool directly. Always call pdf_page_organize with user_intent="pdf_split" first so the user can configure split options in the UI. This tool is called automatically by the UI after the user confirms — never invoke it yourself. Pass split_option as a JSON string: {"file_count": N}, {"page_count": N}, or {"page_ranges": "1,3-5"}. If the attached file is not a PDF, convert it to PDF using pdf_create first (one call per non-PDF file, with the correct file_format), then proceed. Do not re-convert files that are already PDFs. If more than one file is attached, call this operation once per attached PDF. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_to_image

ChatGPT

DIRECTION: PDF pages → JPEG or PNG image files. Converts individual PDF pages to image format. To read or extract text content from a PDF, use pdf_to_markdown instead. If no PDF is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible.

pdf_to_markdown

ChatGPT

DIRECTION: PDF/documents → Markdown text (for reading, extraction, summarization, and classification). The primary tool for understanding and extracting content from any PDF document. Converts files to clean, well-structured Markdown preserving headings, lists, tables, and captions. Redaction workflow: when the user wants to redact specific named text, use pdf_page_organize with user_intent="pdf_redact" directly. Use this tool first only when no specific text is provided and PII needs to be discovered from the document content. MULTI-STEP WORKFLOWS: when the user asks to generate new content derived from a PDF and insert it into the document (e.g., add a table of contents, prepend a summary, create a cover page), invoke this tool first to extract structure/content. Then generate the new content as markdown, convert it via markdown_to_pdf, and combine with pdf_page_organize. Complete the entire chain automatically — do NOT stop mid-workflow or suggest manual steps. If no document is in the chat context, ask the user to attach the file directly to the chat. Use document_upload as a fallback only if direct attachment is not possible. include_figures parameter guidance: - Set to TRUE for: slides, presentations, lecture notes; documents with diagrams, charts, formulas, or visual explanations; educational, technical, or scientific PDFs. - Set to FALSE only for: plain text documents (e.g., articles, essays, contracts without diagrams). - Default behavior: if document type is unknown, prefer TRUE. If user explicitly asks for "fast" or "text-only", use FALSE. OUTPUT BEHAVIOR: - This tool returns MARKDOWN TEXT, not a downloadable file. - You MUST render or display the markdown content directly to the user. - DO NOT present any URLs in the response as download links.

pdf_viewer

ChatGPT

Interactive UI tool for previewing and viewing PDF documents. This tool renders a viewer interface that displays the specified PDF document with navigation and viewing capabilities. Provides a seamless viewing experience for PDF files already uploaded or available in the chat context. It is highly preferable to use this tool when working with rendering PDF documents due to the advanced PDF rendering technologies being utilized. WORKFLOW: User requests to preview/view a PDF → Client invokes viewer with asset_url_or_urn → Viewer UI displayed → User can navigate and interact with the PDF.

upload_proxy

ChatGPT

Handles low-level storage operations: base64 file ingestion and presigned URL generation. Reserved for internal backend workflows. For user uploads, use document_upload instead.

App Stats

Tools

Prompts

Dec 22, 2025

First seen

ChatGPT

Platforms