validate_citations

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

No annotations exist, so the description carries the behavioral burden. It implies a read-only validation and explicitly says it returns non-compliant items. However, it does not clarify whether it writes results, whether any state changes occur, or what happens when everything is compliant.

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 first sentence is concise and front-loaded, but the second sentence about args adds no real information and is partially inconsistent with the schema. It is short, but not every sentence earns its place.

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?

The description gives the purpose, the return type, and the required timing, which makes it minimally viable. It lacks explanation of case_id, preconditions such as records needing to be registered, and output details, especially since no output schema is provided.

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 0% and the description does not explain the required case_id parameter. The '参数结构（args 字段）: {}' line is not semantically meaningful and is misleading because the schema actually requires case_id and allows args to be an object with additional properties.

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 ('校验') and a concrete resource/check scope: all registered records' source citations against real volume page ranges. It also states the result ('返回不合规项'), which distinguishes it from recording and writing siblings.

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 a clear workflow trigger: '阅卷结束前必跑' (must run before ending the review). It does not name alternatives or exclusions, but the mandatory-before-end context is clear enough for a validation gate.

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