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

Annotations provide openWorldHint but nothing about safety/destructiveness. The description compensates by clarifying the metric scope, enumerating exclusions, and giving concrete usage examples with real park names. It could add caveats about data freshness or the year parameter's effect on results, but the exclusion context adds genuine value beyond the annotations.

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 Chinese description is well-organized with clear section markers (涉及指标/类型, 不包含, 典型问法) and front-loads the essential purpose. The pricing block adds some noise but is structurally separated. Every substantive sentence earns its place; only minor redundancy in the three example questions keeps it from a 5.

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 count-query tool with an output schema (which reduces the need to document return values), the description covers the metric definition, exclusions, and usage examples thoroughly. The 100% schema coverage and rich sibling context complete the picture, leaving only minor gaps like behavior around unavailable data or default year logic.

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 baseline is 3. The schema already documents park_name (required) and year (optional integer). The description adds example values and typical questions that ground the parameter semantics, but a query tool like this could reasonably be expected to clarify default behavior when year is omitted.

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 verb+resource: query the count of companies without patents based on a specific park name. It adds essential qualifiers (count only, no list) and provides three concrete example questions, making the tool's behavior unambiguous and distinguishable from its list-returning sibling tools like park_have_no_patent_company_list.

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 typical question patterns and, crucially, an explicit '不包含' (does not include) section that excludes other classification statistics and company list details, implicitly steering users with those needs toward alternative tools. The park_*_list siblings are clear alternatives via naming convention, though no explicit tool name is cited.

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