find_work

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

With no annotations, the description carries the full burden and does well: it discloses the resolution rule (two independent sources must agree before concluding), the failure path (returns a hypothesis plus a follow-up question), and that legitimate purchase links are attached. It omits operational traits such as latency, cost, or auth needs for what is clearly a multi-source lookup.

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?

A single dense sentence that front-loads the purpose and then states input forms, resolution rule, and fallback output in order of importance. No filler clauses; the colon structure makes the behavior easy to parse.

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?

Given a disambiguation-heavy tool with no output schema and no annotations, the description covers what goes in, what success looks like, and what failure returns — enough for an agent to call it correctly. Only peripheral details (output field names, timeout/retry behavior) remain unstated, which is acceptable absent an output schema.

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?

The schema has 0% description coverage on the single 'clue' parameter, so the description must compensate — and it does by specifying that the clue can be a dialogue line, lyric fragment, or plot summary. It could go further with length or format expectations, but the meaning of the parameter is now clear.

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?

States a specific verb (find) plus a concrete resource (shows and songs), and enumerates the accepted clue types (dialogue line, lyrics, plot). It is distinguishable from the verification-flavored siblings (verify_claim, verify_digest) because this tool performs identification rather than checking a claim, though it never names a sibling explicitly.

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 input forms ('凭一句台词、歌词或剧情') imply when to reach for this tool, and the dual-source rule hints at its rigor, but there is no explicit when-not-to-use guidance or comparison against verify_claim/answer_follow_up. The agent must infer routing from the phrasing rather than being told.

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