create_resource
ChatGPTCreate one or more records of a given resource type. Use describe_resource with include: ["schema"] first to learn required and optional fields. Provide a single-item array to create one record, or multiple items for bulk creation. Use productive_domain to discover all available resource types.
create_resource
ChatGPTCreate one or more records of a given resource type. Use describe_resource with include: ["schema"] first to learn required and optional fields. Provide a single-item array to create one record, or multiple items for bulk creation. Use productive_domain to discover all available resource types.
delete_resource
ChatGPTDelete one or more records of a given resource type. Provide a single-item array to delete one record, or multiple items for bulk deletion.
delete_resource
ChatGPTDelete one or more records of a given resource type. Provide a single-item array to delete one record, or multiple items for bulk deletion.
describe_report
ChatGPTDescribe the available fields, groups, filters, sorts, formulas, and custom fields for a report type. Call this before query_report to understand what configuration is available. By default, includable relationships are listed compactly (name and type only). To see available attributes for include_fields, pass include_fields_for with relationship keys to expand.
describe_report
ChatGPTDescribe the available fields, groups, filters, sorts, formulas, and custom fields for a report type. Call this before query_report to understand what configuration is available. By default, includable relationships are listed compactly (name and type only). To see available attributes for include_fields, pass include_fields_for with relationship keys to expand.
describe_resource
ChatGPTDescribe a resource type in the Productive domain — its purpose, fields, relationships, and available actions. Call this to learn how a resource works before querying, creating, or updating records. Without options, returns a compact overview. Include "schema" to get field-level details needed for creating or updating records. Include "related" for relationship descriptions. Include "actions" to discover custom actions (archive, restore, etc.). Use productive_domain to discover all available resource types.
describe_resource
ChatGPTDescribe a resource type in the Productive domain — its purpose, fields, relationships, and available actions. Call this to learn how a resource works before querying, creating, or updating records. Without options, returns a compact overview. Include "schema" to get field-level details needed for creating or updating records. Include "related" for relationship descriptions. Include "actions" to discover custom actions (archive, restore, etc.). Use productive_domain to discover all available resource types.
get_supported_currencies
ChatGPTLists all supported currency codes.
get_supported_currencies
ChatGPTLists all supported currency codes.
load_resource
ChatGPTLoad a single resource by ID. Returns primary attributes only by default. Use include_fields to request relationship attributes (e.g. "assignee.first_name", "project.name"). Use describe_resource to discover available fields and relationships for a resource type.
load_resource
ChatGPTLoad a single resource by ID. Returns primary attributes only by default. Use include_fields to request relationship attributes (e.g. "assignee.first_name", "project.name"). Use describe_resource to discover available fields and relationships for a resource type.
load_skills
ChatGPTLoad full instructions and available actions for one or more skills by id. Skills are specialized domain workflows (e.g. automation-builder), domain guides (e.g. task-creation), or user-authored skills defined by the organization. Call this with every skill id whose description matches what the user needs — up to 5 per call. The response includes each skill's instructions and any actions you can call via perform_action. Prefer one batched call over multiple single-id calls when several skills are relevant.
load_skills
ChatGPTLoad full instructions and available actions for one or more skills by id. Skills are specialized domain workflows (e.g. automation-builder), domain guides (e.g. task-creation), or user-authored skills defined by the organization. Call this with every skill id whose description matches what the user needs — up to 5 per call. The response includes each skill's instructions and any actions you can call via perform_action. Prefer one batched call over multiple single-id calls when several skills are relevant.
perform_action
ChatGPTExecute a registered action by its globally-unique slug (e.g. "send_email", "archive_email_thread", "validate_automation"). Use describe_resource with include: ["actions"] to discover available actions for a resource type. Every action's params are documented in its describe_resource entry.
perform_action
ChatGPTExecute a registered action by its globally-unique slug (e.g. "send_email", "archive_email_thread", "validate_automation"). Use describe_resource with include: ["actions"] to discover available actions for a resource type. Every action's params are documented in its describe_resource entry.
productive_domain
ChatGPTProductive domain reference — all resource types, tool usage patterns, and search strategies. Start here if you are unfamiliar with this server.
productive_domain
ChatGPTProductive domain reference — all resource types, tool usage patterns, and search strategies. Start here if you are unfamiliar with this server.
query_report
ChatGPTQuery a report endpoint to fetch aggregated data. Returns raw report data grouped, filtered, and sorted as specified. Always call describe_report first to understand available fields, groups, filters, and sorts.
query_report
ChatGPTQuery a report endpoint to fetch aggregated data. Returns raw report data grouped, filtered, and sorted as specified. Always call describe_report first to understand available fields, groups, filters, and sorts.
query_resources
ChatGPTQuery resources of a given type with structured filters, sorting, and pagination. Use describe_resource with include: ["schema"] first to learn available filter fields, operators, and their types. Returns a paginated list of matching records. Use productive_domain to discover all available resource types.
query_resources
ChatGPTQuery resources of a given type with structured filters, sorting, and pagination. Use describe_resource with include: ["schema"] first to learn available filter fields, operators, and their types. Returns a paginated list of matching records. Use productive_domain to discover all available resource types.
search_organization_data
ChatGPTKeyword search across organization-wide configuration and metadata. Resolves ambiguous organization-specific terms (e.g. "CRM" could be a team, custom field, or pipeline) that cannot be determined from context alone. Searches across: workflows, workflow statuses, roles, subsidiaries, custom fields, custom field options, teams, document types, service types, holiday calendars, holidays, placeholders, events, pipelines, deal statuses, and saved filters. Returns up to 5 matches per type. Empty results may warrant retrying with alternative terms (broader keywords, synonyms).
search_organization_data
ChatGPTKeyword search across organization-wide configuration and metadata. Resolves ambiguous organization-specific terms (e.g. "CRM" could be a team, custom field, or pipeline) that cannot be determined from context alone. Searches across: workflows, workflow statuses, roles, subsidiaries, custom fields, custom field options, teams, document types, service types, holiday calendars, holidays, placeholders, events, pipelines, deal statuses, and saved filters. Returns up to 5 matches per type. Empty results may warrant retrying with alternative terms (broader keywords, synonyms).
search_project_data
ChatGPTKeyword search across project-scoped configuration and structures within a specific project. Finds task lists, folders, custom fields, workflow statuses, and other project-specific data. Resolves ambiguous project-specific terms (e.g. "Backlog" could be a folder, task list, or workflow status). Returns up to 5 matches per type. Empty results may warrant retrying with alternative terms (broader keywords, synonyms).
search_project_data
ChatGPTKeyword search across project-scoped configuration and structures within a specific project. Finds task lists, folders, custom fields, workflow statuses, and other project-specific data. Resolves ambiguous project-specific terms (e.g. "Backlog" could be a folder, task list, or workflow status). Returns up to 5 matches per type. Empty results may warrant retrying with alternative terms (broader keywords, synonyms).
search_records
ChatGPTKeyword and semantic search across records by name or text content. Does NOT filter by properties, type, or status — query/filter tools are suited for property-based lookups. The "type" parameter accepts multiple types for cross-type or ambiguous searches. "keywordSearchQuery" is the primary input; "semanticSearchQuery" can be added alongside it when phrasing may differ from actual record names — "semanticSearchQuery" alone may not be available. For pages/docs, type "page" returns results with page hierarchy. For people: type "person" covers logged-in users (employees, contractors, clients); type "contact" covers CRM contacts (people without login access). Pick the one that matches the user's intent; include both only when the intent is genuinely ambiguous. Empty results may indicate keyword mismatch — alternative terms, synonyms, or broader keywords often succeed. Use "deepSearch: true" with "keywordSearchQuery" to search within record content (task descriptions, page body text), not just record names — useful when the term appears inside a record rather than in its name. Has no effect with "semanticSearchQuery" (semantic search already searches within content by nature).
search_records
ChatGPTKeyword and semantic search across records by name or text content. Does NOT filter by properties, type, or status — query/filter tools are suited for property-based lookups. The "type" parameter accepts multiple types for cross-type or ambiguous searches. "keywordSearchQuery" is the primary input; "semanticSearchQuery" can be added alongside it when phrasing may differ from actual record names — "semanticSearchQuery" alone may not be available. For pages/docs, type "page" returns results with page hierarchy. For people: type "person" covers logged-in users (employees, contractors, clients); type "contact" covers CRM contacts (people without login access). Pick the one that matches the user's intent; include both only when the intent is genuinely ambiguous. Empty results may indicate keyword mismatch — alternative terms, synonyms, or broader keywords often succeed. Use "deepSearch: true" with "keywordSearchQuery" to search within record content (task descriptions, page body text), not just record names — useful when the term appears inside a record rather than in its name. Has no effect with "semanticSearchQuery" (semantic search already searches within content by nature).
search_resource
ChatGPTSearch for resources of a given type by keyword or semantic query. Use keyword_query for exact/fuzzy text matching. Use semantic_query for meaning-based AI search. Use describe_resource with include: ["schema"] to learn which search modes a resource supports.
search_resource
ChatGPTSearch for resources of a given type by keyword or semantic query. Use keyword_query for exact/fuzzy text matching. Use semantic_query for meaning-based AI search. Use describe_resource with include: ["schema"] to learn which search modes a resource supports.
update_resource
ChatGPTUpdate one or more records of a given resource type. All provided fields are treated as changed — no need for a separate dirtyFields list. Use describe_resource with include: ["schema"] first to learn available fields. Provide a single-item array to update one record, or multiple items for bulk update.
update_resource
ChatGPTUpdate one or more records of a given resource type. All provided fields are treated as changed — no need for a separate dirtyFields list. Use describe_resource with include: ["schema"] first to learn available fields. Provide a single-item array to update one record, or multiple items for bulk update.
