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

Annotations only provide openWorldHint=true, which is minimal. The description adds context about the metric (专精特新企业数量) and what's not included (其他企业分类, 企业名单明细). It doesn't describe return format (though output schema exists), pagination, or any potential edge cases (e.g., year could be null). With sparse annotations, the description carries partial burden but could be more explicit about behavior.

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?

Description is concise, two lines plus examples. It front-loads the purpose and then provides exclusions and examples. The pricing info is extra but may be useful. No fluff, each sentence adds value. Slightly less than 5 because the pricing block could be considered external but it's relevant info.

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 simple count tool with 1 required param and output schema present, the description covers the main usage scenario, exclusions, and examples. It doesn't specify edge cases (e.g., what if park name doesn't match?), but with the output schema available and typical query patterns given, it's sufficiently complete for this tool type.

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 parameters have descriptions with examples). The description provides context on the metric and excludes, but doesn't add additional param-specific semantics beyond what schema already provides. The year parameter is optional and document in schema; description doesn't add constraints (e.g., valid ranges). Baseline 3 due to 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 clearly states the tool counts specialized enterprises based on a specific park name, and lists the indicator type. It distinguishes from sibling tools like park_specialized_company_list (which would return the list) and park_high_tech_company_num (different metric). However, it doesn't explicitly name sibling tools, only implying the distinction by mentioning 'excludes other company classification statistics'.

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?

Provides typical example queries (中关村软件园专精特新企业有多少) and explicitly states what is excluded (其他企业分类的统计；企业名单明细). It implies when to use (when asking for count of specialized enterprises in a park) versus when not (list details). It doesn't explicitly name alternatives like park_specialized_company_list, but the exclusions clarify scope.

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