answer_with_sources
ChatGPTRetrieve and organize verifiable judicial passages with sources and version provenance. When allowed_modes is omitted, retrieval defaults to natural hybrid thematic search. Use allowed_modes=['judicial_text'] for explicit textual retrieval; require_semantic is preserved when supplied. Does not provide legal advice or determine the outcome of the user's case.
list_courts
ChatGPTList visible Spanish judicial bodies and their counts within the available corpus.
list_source_groups
ChatGPTList configured legal sources and their availability status; availability does not imply complete coverage.
lookup_administrative_document
ChatGPTRetrieve a specific tax administrative document by DGT:consultation-number or DYCTEA:registry. Also accepts bare consultation/registry numbers, partial DYCTEA procedure references and official criterion URLs/identities. Returns identity, metadata and any available excerpt. Ambiguity returns identified candidates; select their id or full registry. Not found does not establish absence from the official source.
lookup_decision
ChatGPTRetrieve a resolution by ID, ECLI, ROJ, resolution number or case number. Never invent an ECLI. Ambiguity returns candidates with decision_type, chamber, section, decision_number, case_number and matched_identifier_types. Filter decision_type=sentencia or auto; identifier_type distinguishes resolution number from case number. Select a candidate ID/ECLI. Court accepts codes such as TC and TS or exact unambiguous catalog names. Not found does not prove absence from the official source.
read_administrative_document
ChatGPTRead version-pinned literal administrative passages. Select tax_answer for the DGT answer, administrative_criterion for a TEA criterion, or legal_grounds for resolution grounds when available. Returns 1 to 5 paragraphs per page and identifies available sections. Facts and questions do not establish the answer. Source classification alone does not establish validity or applicability.
read_decision
ChatGPTRead literal paragraphs from a specific judgment version and section. Optional q anchors the initial read near the topic; inspect prefix_omitted and continue with the returned offsets. Check available_sections and warnings; summaries are not full judgments.
search_administrative_documents
ChatGPTSearch Spanish tax administrative doctrine. Use source_groups=['petete'] for DGT interpretations and binding consultations; ['dyctea'] for TEAC/TEAR/TEAL criteria and economic-administrative appeals; omitting the filter searches both. Results contain references and indexed excerpts. Coverage is progressive.
search_decisions
ChatGPTSearch Spanish and EU court judgments by legal issue, terms, body, date or source. Filter countries with ES, EU or both. Optional source_groups accepts only boe_tc, cendoj, tc_hj, curia; omit it to search all judicial sources. The judicial corpus excludes DYCTEA and PETETE. Returns matching decisions with identifiers, metadata, official links, and indexed excerpts. Free-text query defaults to natural hybrid thematic retrieval, requiring vectors and limited to a window of up to 50 decisions. Select search_mode=strict explicitly for textual operators and phrases. query_intent implies strict when search_mode is omitted; do not combine query_intent with explicit natural. The original free-text query is preserved; retrieval does not establish legal interpretation or exhaustive coverage. query_intent supports required, alternative, phrase and excluded terms.
search_evidence
ChatGPTSearch judicial passages with official links, versions and content_scope. When the user restricts a court, send body_code='TS' for Tribunal Supremo (court is an alias); writing the court in query does not filter results. Each call accepts one court code. court_scope='all' enables contextual court mentions without a court restriction. applied_filters identifies the applied scope. CENDOJ summaries are identified separately from full judgments. Omitted allowed_modes defaults to natural hybrid retrieval; use allowed_modes=['judicial_text'] for explicit textual retrieval. allowed_modes accepts judicial_text, semantic_vector and judicial_hybrid.
answer_with_sources
Claudelist_courts
Claudelist_source_groups
Claudelookup_administrative_document
Claudelookup_decision
Clauderead_administrative_document
Clauderead_decision
Claudesearch_administrative_documents
Claudesearch_decisions
Claudesearch_evidence
Claude