OpenCase

The descriptions are unusually careful about cross-referencing and separating overlapping tools: detect_legal_citations vs verify_citations_in_text, resolve_legal_citations vs verify_citations_in_text (list vs prose), and check_case_validity vs get_case_treatments are all explicitly distinguished. The only soft overlap is between research_legal_question and review_document_against_law, both of which research law, though one takes a question and the other a document.

Every tool follows a clean verb_noun snake_case pattern (check_case_validity, detect_legal_citations, get_case_treatments, resolve_legal_citations, verify_citations_in_text, search_dockets, etc.). No mixing of conventions or casing styles.

Eleven tools is well-scoped for a legal research and cite-checking server, with each tool covering a distinct operation. No redundant or filler tools are present.

The surface covers the cite-checking lifecycle well: detection, resolution, verification, quote checking, good-law validity, treatment analysis, authority reading, docket search/filing retrieval, and document review. The main gap is the absence of a keyword/topic case-law search (authority retrieval requires already knowing a citation), though research_legal_question partially compensates.