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

The description discloses the output scope by stating it returns only a count and excludes lists and other enterprise classification statistics. It also includes per-run pricing information, which is useful behavioral context. Since annotations only include openWorldHint, the prose carries most of the responsibility and does a reasonably good job for a simple count query.

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 compact and front-loaded with the core metric, followed by exclusions and examples. The structure is easy to scan. The pricing JSON is slightly extraneous but does not harm comprehension. It could be even better if explicit sibling alternatives were mentioned, but overall it is efficiently written.

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 tool is simple and well-described for the agent context. The description covers the metric, specific park scope, excluded outputs, and representative user questions. Given the rich list of sibling tools and the presence of the listed in the tool name, the description gives enough context to select the correct tool for a count-only patent query.

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%, so the schema itself already documents park_name and year. The description adds useful sample phrasings and clarifies the metric type, but it does not significantly extend parameter semantics beyond what the schema already provides.

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 that the tool counts the number of enterprises that own patents by a given park name. It also differentiates from sibling tools by explicitly saying it is count-only and excludes company list details, which distinguishes it from park_have_patent_company_list and other park_*_num 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 gives concrete typical user questions like '中关村软件园拥有专利的企业有多少', which clarify when to use the tool. It explicitly lists what is not included, such as other classification counts and list details, which provides useful when-not-to-use context; however, it does not explicitly name alternative tools like park_have_patent_company_list.

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