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

Beyond the openWorldHint annotation, the description discloses the merged output structure (total/production/sales/dependent text), explicit exclusions, and concrete pricing of 100 credits per run, giving the agent operating-cost and output-format expectations. It does not contradict the annotations, and adds meaningful context not available in structured fields.

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 content is organized into clear sections and is front-loaded with the purpose statement. However, the metric breakdown is redundant (stated both inline in parentheses and again as a bulleted list), and the pricing JSON block adds visual noise, making the description longer than necessary for the incremental value it provides.

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 an output schema, the description covers purpose, region granularity (country/province/city/county), the four metric types returned, exclusions, typical user phrasings, and cost. Combined with 100% schema coverage and an output schema, the agent has sufficient context to invoke the tool correctly. Minor gaps exist around empty-result handling, but the description is functionally complete.

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 '典型问法' examples do demonstrate natural-language-to-parameter mapping (e.g., '2024年' → year, '全国' → region), but the schema descriptions already include inline examples for region and chain_name, so the description adds marginal value beyond what's already structured. Baseline of 3 is appropriate.

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 states a specific verb+resource+scope: it queries the count of enterprises surviving 5+ years filtered by region and industry chain name. It distinguishes from siblings by explicitly framing itself as a count query ('企业数量') that merges four metric types, while the '不包含：...企业名单明细' clause clearly differentiates it from the chain_year5_company_list variant.

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 '不包含：其他企业分类的统计；企业名单明细' clause provides clear when-not guidance, signaling that list-level or other-classification queries should go elsewhere. However, it never explicitly names an alternative tool like chain_year5_company_list, relying on the sibling naming convention rather than spelling out 'use X instead', so it stops short of a 5.

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