find_mentionsReturn source-linked places where a person, place, event, work, institution, or concept is mentioned.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | ||
| author | Yes | ||
| entity | No | ||
| work_id | No | Optional work filter. | |
| entity_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| count | No | ||
| entity | No | ||
| mentions | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate safe read operation (readOnlyHint, destructiveHint false). Description adds 'source-linked' context but doesn't elaborate on behavioral aspects like result ordering, pagination, or what constitutes a 'mention'. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is highly concise with no extraneous words. Appropriately front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters, 1 required, and an output schema present, the description is too sparse. It omits crucial context like how parameters relate to each other, the meaning of 'source-linked', and how results are presented. Incomplete given tool complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 17% (only work_id described). Description does not explain the roles of query, author, entity, entity_id, or limit. Users cannot determine how these parameters interact or which combination to use for a specific mention search.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool returns mentions of various entity types in sources, with a specific verb 'return' and resource 'source-linked places'. It distinguishes from sibling tools like search_corpus (general text search) or get_allusions (specific allusion type).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like search_entities or get_crossrefs. Missing context about typical use cases or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct aspect of the corpus: general search vs. specific entity search, passage retrieval vs. work metadata, allusions vs. cross-references, etc. No two tools appear to do the same thing.
All tool names follow a consistent verb_noun pattern (e.g., list_authors, search_corpus, get_passage) and use snake_case throughout, making the set predictable and easy to navigate.
With 19 tools, the server is slightly above the ideal 3-15 range, but each tool covers a necessary function for a rich text corpus API (search, retrieval, cross-referencing). No tools feel redundant or excessive.
The tool surface comprehensively covers the domain: listing authors/works, searching for passages/entities/Greek phrases/letters, retrieving full passages, work metadata, allusions, crossrefs, parallel texts, citation formatting, and AI evidence pack building. No obvious gaps are present.