GoVeda Patent

Get up to 25 patents as structured data without rendering a card. More efficient than calling get_patent repeatedly; use show_patent when the user should see a card or comparison table. Use sections to request only the parts needed. Available sections: metadata, legal_status, abstract, claims, description, dates, parties, classifications, legal_events, family. Use 'all' for everything. `legal_status` selects the current status returned alongside fixed metadata; `legal_events` selects the separately paged history. Section-owned response fields: legal_status → legal_status; abstract → abstract; claims → claims; description → description; dates → filing_date, publication_date, dates; parties → inventors, current_assignees, original_assignees, applicant; classifications → classifications; legal_events → legal_events; family → family_scope, family. Choose sections based on user intent: - Titles or basic record metadata only → ["metadata"] - Patent overview → ["abstract", "dates"] (default) - Detailed comparison → ["abstract", "claims", "description"] - Inventor/assignee comparison → ["parties"] - Current legal status → ["legal_status"] - Legal/expiry history → ["legal_events", "dates"] - Related patents → ["family"] - Everything → ["all"] Fixed metadata accompanies every successful row, so do not add 'metadata' to another selection; if a host does, the redundant value is ignored. Long text uses max_chars per row (default 8,000; range 1,000–64,000), then fairly divides a 60,000-character aggregate ceiling across every requested row. List sections use limit (default 50; range 1–200). family_scope selects simple/DOCDB (default) or extended/INPADOC. Returns a PatentBatch object: {"results": [BatchPatentContent, ...]}. On success publication_number, url, and publication_type are always set when available (regardless of sections), while title may be null when the source document has no title. Use sections=['metadata'] to return only those fixed metadata fields. Fields belonging to unrequested sections are omitted; a requested section that completed without source data is returned explicitly as null or an empty list. On row failure, the row carries a structured error with message/code/suggestion. If the whole batch fails, PatentBatch.error is set and results is empty. When a requested section is temporarily unavailable, its field is omitted and the failure is reported in that row's `section_errors`.

batch_get_patents

Check the current status and progress of a novelty report. Pass the report_id from generate_novelty_report. Returns status and progress details only — use get_report_summary for the full assessment once status is 'completed'. Polling guidance: wait 30s if pending/searching/analyzing_query/analyzing_final, wait 60s if analyzing_patents.

get_report_status

Check status of a search or prior art analysis. Returns results if completed. Pass the search_id from semantic_patent_search or prior_art_search. Each call returns the current state without waiting for search completion. If status is reranking, wait 30s and retry. Results include publication_number, title, relevance score, and URL.

get_search_status

Verify canonical assignee (company) names exist and count their patents. Deterministic — no LLM, no web; same input returns the same output. USE FOR: confirming a company is a stored assignee and how many patents it holds, optionally narrowed by date/jurisdiction/classification/status filters, optionally broken down per jurisdiction. NOT FOR: resolving a free-text company name (use lookup_party first), or fetching the patents themselves (use party_patents). Call lookup_party to resolve each name. Matching is exact except that each name also matches its ALL-CAPS storage form, covering patent offices that retain raw applicant casing; other spelling, punctuation, and transliteration variants are not inferred. An unknown name is reported per-name (exists=false, patent_count=0), never as an error; `exists` distinguishes an unknown name from a real one filtered to zero. Batch up to 50 names per call, counted individually. `total` is the union over patents that have a publication date (a patent held by several listed names counts once) — list a company's stored variants together for a merged view. breakdown='authority' adds per-jurisdiction counts.

party_count

Find available patent publication candidates for one or more unresolved references. This tool returns possibilities for review; it does not prove that a candidate is the same patent as the supplied reference and does not select a candidate.

discover_patent_references

Generate a novelty/patentability assessment for an invention idea. Submits async report. NOT for: simple patent search (use semantic_patent_search). Async: returns report_id immediately. Poll with get_report_status. 5-15 minutes typical. IMPORTANT: The report is AI-assisted and is NOT legal advice. Always inform the user that results should be reviewed by a qualified patent attorney.

generate_novelty_report

Get BACKWARD non-patent-literature (NPL) citations — papers, books, standards etc. THIS patent cites. NPL exists only on the backward direction. Paginated: returns one page; use pagination.next_offset to fetch more. Returns a BackwardNplCitationsPage: 'citations' is a list of {text, source, category, author, title, date}. On failure check the nested error object for message/code/suggestion/details.

get_patent_backward_npl_citations

Get BACKWARD patent citations — patents THIS patent cites (patents only; for NPL use get_patent_backward_npl_citations). 'cited_in' is the authoritative structure for every source family member, citation-report source, category, and related-claims occurrence. 'categories' is a derived list of unique non-empty cited_in category codes ordered X, Y, A, then other categories. ORDER uses examiner-category priority where available: X first, then Y, then A, then citations without X/Y/A; ties use publication number. This prioritizes search-report classifications, not semantic similarity. Complete category provenance remains in 'cited_in'. Paginated: returns one page; use pagination.next_offset to fetch more. Returns a BackwardPatentCitationsPage: 'citations' is a list of {publication_number, url, categories, cited_in, title, publication_date, legal_status, publication_type}. When a row's 'url' is present, render it as a Markdown link [publication_number](url). On failure check the nested error object for message/code/suggestion/details.

get_patent_backward_patent_citations

Get content of a specific patent by publication number. Use 'sections' to request only the parts needed. Available sections: metadata, legal_status, abstract, claims, description, dates, parties, classifications, legal_events, family. Use 'all' for everything. `legal_status` selects the current status returned alongside fixed metadata; `legal_events` selects the separately paged history. Section-owned response fields: legal_status → legal_status; abstract → abstract; claims → claims; description → description; dates → filing_date, publication_date, dates; parties → inventors, current_assignees, original_assignees, applicant; classifications → classifications; legal_events → legal_events; family → family_scope, family. Choose sections based on user intent: - Title or basic record metadata only → ["metadata"] - Patent overview → ["abstract", "dates"] (default) - Detailed technical analysis of selected parts → ["abstract", "claims", "description"] - The complete text, to read, summarize, or compare the whole patent → use get_patent_full_text - Who invented/owns it → ["parties"] - Current legal status → ["legal_status"] - Legal/expiry history → ["legal_events", "dates"] - Related patents → ["family"] - Everything → ["all"] Fixed metadata accompanies every successful result, so do not add 'metadata' to another selection; if a host does, the redundant value is ignored. NOT for: topic search (use semantic_patent_search), multiple patents (use batch_get_patents), reading the complete text (use get_patent_full_text, one call without cursors), locating a term inside one patent (use search_patent_content). Long text (abstract, claims, description) shares one body-text char budget (`max_chars`, default 16000; range 1000-64000) that waterfalls in that order; anything cut or omitted is itemized in `truncations` with a `next_cursor`. Calls remain bounded and do not auto-continue: use this tool when you can stop once the evidence is sufficient. When the complete text is needed, call get_patent_full_text instead of following cursors. `completion_required` is deprecated and kept only for compatibility. A single-section call gets the whole budget, and cuts land on whole claims / paragraph boundaries — a paragraph longer than the remaining budget is returned whole rather than split, so `description` can exceed max_chars; its truncations entry reports the actual shown_chars. `max_chars` does not cap the entire serialized tool output: patent metadata, structured sections, progress/truncation fields, and JSON framing add overhead outside the body-text budget. List sections (family, legal_events) page independently via `limit` (default 50, max 200); when a list has more members, its truncations entry carries a non-null next_cursor. For family, `family_scope` selects simple/DOCDB (default) or extended/INPADOC. Paragraph-precise fetch: pass `paragraph_numbers` (max 20, implies description) with values from a previous response — only paragraphs the source document itself numbers can be addressed this way. Returns structured data without rendering a card; use `show_patent` for display. Publication numbers use hyphenated UCID format (for example WO-2015179075-A1), including family members. On success: publication_number, url, and publication_type are always set when available (regardless of sections); title may be null when the source document has no title. Use sections=['metadata'] to return only those fixed metadata fields. Fields belonging to sections that were not requested are omitted. A requested section that completed without source data is returned explicitly as null or an empty list. If a requested section is temporarily unavailable, its data field is omitted, other content is preserved, and `section_errors` identifies the section with code `UPSTREAM_UNAVAILABLE` and `retryable: true`. A successfully fetched family with no members is `family: []`. On failure, nested `error.{message,code,suggestion,details}` is set instead and patent data fields are omitted; callers should check `error` before reading patent data.

get_patent

Get FORWARD citations — patents that CITE this patent (patents only, no NPL). Paginated: returns one page; use the returned pagination.next_offset to fetch more. Forward citations can number in the thousands for foundational patents, so page through rather than expecting everything in one call. USE FOR: who-cites-this, impact/influence, downstream patents. For what THIS patent cites, use get_patent_backward_patent_citations / get_patent_backward_npl_citations instead. ORDER IS BY PUBLICATION NUMBER, not relevance or date — the first page is NOT the most important citing art. Returns a ForwardCitationsPage: 'citations' is a list of {publication_number, url, source, title, publication_date, legal_status, publication_type}; 'pagination' carries total/has_more/next_offset. When a row's 'url' is present, render it as a Markdown link [publication_number](url). On failure check the nested error object for message/code/suggestion/details.

get_patent_forward_citations