works_search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations supplied, the description carries the full behavioral burden and does so unusually well: it discloses the ~300-item cap per category, the merge ordering, 10-minute result caching so paging doesn't re-request, the server-side stuck-page failure surfaced as `incomplete`, and the lifetime of short refs (valid only for this MCP service run) plus how to resolve them via image_view. These are exactly the non-obvious traits an agent needs before calling.

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?

The description is dense but front-loaded: purpose first, then the no-category behavior, then pagination/caching caveats, then sibling routing, then ref handling. Nearly every clause carries a distinct operational fact, though the merge-order and 300-cap detail could be tightened without losing meaning.

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?

For an 8-parameter, annotation-free search tool with no output schema, the description compensates by naming the returned fields (found_in, total, by_category, matched_queries, incomplete, *_ref refs) and the pagination contract. Nothing an agent needs in order to call it correctly or interpret its results is missing.

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 coverage is 100%, so the schema already documents each parameter; the description still adds real meaning beyond it, notably the consequence of omitting category_id (search-all with dedupe), the 8-term cap on queries and the matched_queries annotation returned per item, and that offset/count paging is served from cache. Only instance_id and project_path are left entirely to the schema.

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?

The opening clause states a specific verb and resource ("按作品名搜索首页作品") and pins the exact backend semantics ("与首页搜索框同一个接口"). It also differentiates from siblings by naming works_by_effect for effect-ID lookups and by deferring field semantics to works_list, so an agent can choose among the three without opening any schema.

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?

It gives explicit conditions: omit category_id to search all categories with merge/dedupe, use queries for up to 8 terms, and use works_by_effect when searching by effect ID. What it doesn't spell out is when to prefer works_search over works_list or library_search for a plain browse, leaving that routing to inference from "其余字段同 works_list".

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.