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

Annotations only provide openWorldHint, so the description carries most behavioral disclosure. It frames the operation as a query ('查询'), enumerates the exact metrics covered, and explicitly excludes related categories (recruitment, contract/overtime/injury safeguards, batch screening), giving the agent a clear expectation of what the tool will and will not return. It does not detail time-range semantics behind '周期变化', but the output schema covers return structure.

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 well-structured with a main statement, inclusion list, exclusion list, examples, and pricing. It is mostly efficient, though the '涉及指标/类型' list partly repeats the first sentence and three typical questions are more than necessary.

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 2-parameter tool with a full output schema and strong sibling differentiation, this description is complete enough: it defines scope, exclusions, and examples. It leaves minor ambiguity about the meaning of '周期变化' (periodic changes) but does not need to explain return values given the 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?

Schema description coverage is 100%: both required parameters have clear descriptions and examples (e.g., '比亚迪股份有限公司' and '中国'). The description's typical questions mirror these examples and add no substantive parameter semantics beyond the schema.

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 a specific purpose: query employer-brand periodic changes for a named company and country, covering per-employee salary, benefits, and vacation days. It also explicitly lists exclusions, distinguishing it from sibling enterprise_change_* tools.

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 negative guidance ('不用于招聘动态...劳动合同签订或加班伤亡等保障指标') and non-goals ('不包含：非本分类指标；按园区/产业链批量筛企业名单'), plus typical question examples. This effectively tells the agent when not to choose this tool over alternatives.

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