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

With annotations limited to openWorldHint, the description must clarify what the tool actually returns. It says both 'A级纳税人企业列表' and '仅返回数量不返回名单' in the same definition, so the agent cannot confidently infer whether the result is a list of companies, a count, or both. Scope exclusions are mentioned, but the central behavior is contradictory.

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 short, front-loaded with the main purpose, and the typical question examples are useful. It is not too verbose, though '涉及指标/类型' somewhat repeats the first sentence, and the embedded pricing block adds noise.

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?

Because the sibling set includes both park_a_taxpayer_company_list and park_a_taxpayer_company_num, the description needed to explicitly say whether this tool returns the list or only a count. The contradictory sentence leaves the definition incomplete and makes correct tool choice ambiguous even though the parameter schema and output schema exist.

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 input schema already documents both parameters with 100% coverage: park_name is a required string with concrete examples, and year is an optional integer. The description adds some real-world phrasing but does not materially improve on the schema, so the baseline score of 3 applies.

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 first sentence clearly names the target: query an A-level taxpayer company list based on a specific park name, and the typical questions reinforce this. However, the later phrase '仅返回数量不返回名单' directly conflicts with the tool name and the list-oriented examples, so the purpose is not fully unambiguous.

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 '典型问法' examples provide some useful context, and the '不包含' clause gives a scope limitation. But there is no explicit guidance about when to choose this list tool versus the direct sibling 'park_a_taxpayer_company_num', and the confusing statement about returning only a count versus a list makes the selection guidance unreliable.

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