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

The description contradicts the tool's name and its own '列表查询' claim by saying it returns only a count, not a list. This obscures actual behavior and creates confusion about output. Annotations are limited to openWorldHint=true, which offers no additional safety or behavioral context, so the description fails to provide correct behavioral disclosure.

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 but contains a harmful contradiction. While not verbose, the misleading statement '仅返回数量不返回名单' undermines the entire text and reduces its usefulness. A concise but erroneous message is scored low on effectiveness.

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 fails to clarify whether the tool returns a list or a count, which is a key behavior. It does not describe the output schema (even though one exists) or mention pagination, error handling, or prerequisites. The presence of a sibling 'num' tool underscores the need for explicit differentiation, which is missing.

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?

Input schema covers 100% of parameters with clear descriptions (park_name examples and year). The description adds little beyond re-stating park name usage, and provides no further semantic detail (e.g., year range, valid formats). Baseline 3 is appropriate given high schema coverage.

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 claims to query a list of specialized and new enterprises in a park (says '列表查询' and provides typical questions), but then states '仅返回数量不返回名单' (only returns count, not names). This directly contradicts the tool's name and stated purpose of returning a list, making it unclear whether the tool returns a list or a count.

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?

Typical example queries are given, which imply when to use it (park-specific specialized company list). However, no explicit guidance contrasts it with the sibling tool 'park_specialized_company_num' (which likely returns only counts). The statement '仅返回数量不返回名单' is misleading and suggests the tool actually behaves like the num variant, confusing usage.

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