find_capability

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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses the key trait that matching is synonym-tolerant and colloquial ('论文' → academic resources, '借书' → library), which an agent could not infer elsewhere. However it never says what comes back (a ranked capability list? command names? one match?) and gives no indication of scope limits, so the transparency is partial.

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?

One sentence, front-loaded with the routing purpose before the parenthetical on synonym support. Nothing is padding; the example pairs are the shortest possible demonstration of the synonym behavior.

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 lightweight discovery tool with no annotations and no output schema, the description covers purpose and usage well. The notable gap is that the response shape is undefined in both description and structured fields, so an agent cannot predict whether it receives tool names, capability descriptions, or ranked suggestions – a meaningful omission for a router whose whole job is producing a next step.

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% for the single 'query' parameter, so the schema already defines it and supplies the same style of examples (作业 / 论文 / 班车 / 待办 / 预约). The description reinforces that natural-language or colloquial keywords are acceptable, which adds mild value, but the baseline of 3 applies when the schema does the documenting.

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 names a specific verb and resource in a compact formula – '需求→能力路由' (need-to-capability routing) – and immediately defines what it searches over: which command/tool a need belongs to. It is unambiguous and clearly distinct from every sibling, which are concrete domain tools rather than a routing layer.

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 an explicit trigger condition: use it first when you are unsure which command/tool a requirement maps to. What is missing is the complementary clause – that you should skip it when the target tool is already known – and any guidance on what to do with the result once returned.

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