catalog_lookup

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses that the tool returns a candidate list with relevance scores and hit signals, and details the scoring logic (name exact/prefix/alias hits > summary token hits > popularity adjustment). However, it does not fully define what 'hit signals' are, and omits potential edge behaviors such as no-match handling or request limits beyond the schema's limit parameter.

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 concise and front-loaded with the primary action and results. It packs essential usage information (when to use, result ordering, scoring rationale) into two sentences without redundancy. Every sentence adds value, and the structure is clear.

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 a search tool with 2 parameters, no output schema, and no annotations, the description is complete: it explains the search input, the output (candidate list with scores and hit signals), the ranking algorithm, and the workflow with doc_extract. The only minor gap is the exact definition of 'hit signals,' but that is not critical for using the tool correctly.

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 100%, with both parameters (query and limit) already described in the input schema. The description adds no extra parameter semantics beyond what the schema provides; it merely restates that query can be a name or description, which is already in the schema. Therefore the baseline of 3 is appropriate.

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 description clearly states the tool searches a documentation catalog by library/framework name or description, and returns candidate lists with relevance scores and hit signals. It explicitly distinguishes from sibling doc_extract by describing the intended workflow (use this first, then pass the returned id to doc_extract), and the resource is specific (documentation catalog).

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?

The description provides explicit when-to-use guidance: '当不确定库的规范 id 时，先调用本工具' (call this tool when unsure of the canonical id), and names the alternative/next step: use the returned id to call doc_extract. It also explains the ranking order, which helps set expectations for result interpretation.

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