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

With only openWorldHint in annotations (vague), the description carries the burden and adds value by detailing the multi-category aggregate return format, explicit exclusions, and example queries. It discloses the combined text return structure clearly, though it doesn't discuss data sources, update frequency, or edge cases like missing data.

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 well-organized with clear sections (function, metrics, exclusions, examples, pricing), making it scannable. The pricing block adds minor noise but is useful operational info. Front-loaded with the core function, though the multiple sections could be trimmed slightly.

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 3-parameter count tool with multiple output categories, the description covers what it does, what it returns (aggregate categories), what it excludes, and provides realistic example queries. It could be more complete with explicit parameter constraints or output formatting details, but the output schema (not shown) presumably handles that. Overall, fairly comprehensive given context signals.

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% and each parameter has terse but sufficient description (e.g., region example '「全国」「成都」', chain_name example '「集成电路」'). The description's typical questions add example values but don't drastically exceed the schema coverage; the year parameter is only illustrated in examples, not in the main description.

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 queries the count of patent-owning enterprises filtered by region and industry chain, with a specific verb+resource structure. It explicitly lists included metrics (total/production/sales/dependent types) and excludes others (other classifications, detail lists), distinguishing it clearly from sibling tools like chain_have_copyright_company_num.

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 'Not included' section sets clear boundaries, and the three example questions demonstrate appropriate use cases (e.g., 'How many enterprises in Chengdu's new energy industry chain own patents?'). However, it doesn't explicitly name alternative tools or state when NOT to use this tool, though the examples guide selection well.

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