judge_set

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

No annotations exist, so the description carries the full burden. It usefully discloses that judging is deterministic and rule-bounded and that only rule-attributable error causes are returned, but says nothing about whether the result is persisted, whether the call is idempotent, or what happens if the passage was not ingested.

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?

Three short sentences, front-loaded with the purpose and followed by the routing instruction and the return summary. No filler, though '一整篇' and the parenthetical rule list are a little compressed.

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?

Without annotations or an output schema, the description does sketch the return (per-question results plus rule-determinable causes), but it leaves the sole input undocumented and the mutation semantics unclear, which is thin for a scoring/judging tool.

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?

There is one required parameter, review_id, with 0% schema description coverage, and the description never mentions it or explains where the id comes from. With schema coverage this low the description needed to compensate and does not.

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 (judge) and scope (an entire passage/set) plus the rule categories applied: word count, singular/plural, spelling, and true/false label conventions. The line '对错只能由这里判' implicitly distinguishes it from siblings like submit_explanation or set_cause, though no sibling is named.

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?

Explicitly tells the agent to use this tool rather than judging correctness itself ('不要自己判'), which is a real routing directive. It does not state prerequisites such as whether the review must be ingested first or whether re-judging is allowed.

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