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

The description discloses behavior: it returns a list of companies, not counts, and excludes other enterprise classifications. It mentions the time frame '近两年' (last two years). However, with only the openWorldHint annotation (which is a structural hint), the description carries the burden of behavioral disclosure. It doesn't describe return format, pagination, or what happens when no data is found. It also embeds pricing info in the description, which is metadata that could be better placed in annotations, but that's minor. Overall, it adds some context (list vs. count, exclusions) but lacks detail on response behavior or edge cases.

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 concise and front-loaded with the core purpose. It uses a clear structure: purpose, what's included, what's excluded, and typical queries. The pricing section is embedded but doesn't clutter the core description. It's efficient - every sentence serves a purpose - though the pricing info could arguably be moved to annotations, and the phrasing '涉及指标/类型' is a bit redundant. Overall, it's well-structured and wastes no words.

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?

Has an output schema (listed in context) which covers return structure, so that's handled. Given the tool has 2 params (one optional), a clear purpose, and explicit exclusions, the description covers the main usage. However, it doesn't explain the distinction from the chain_issued_tender_company_list sibling (though the park context makes it inferable), and it doesn't mention if the '近两年' is fixed relative to current date or if the 'year' parameter overrides that. Also, it doesn't clarify what '发起过招标' means precisely (issued tenders vs. participated). Given the sibling context and potential ambiguity, a 3 is appropriate - complete for basic use but leaves some nuances unclear.

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 coverage is 100% - both 'year' and 'park_name' have descriptions in the schema. The description adds the context that 'year' is optional (though schema also shows it's not required) and examples of park names. However, it doesn't go beyond the schema for parameter details like format of the year value or whether the year is exactly the year of the tender, or if it's the year relative to the query date. The description does add the '近两年' time frame which clarifies the default, which is helpful. Given the schema already documents the parameters well, 3 is appropriate as the description adds marginal value.

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's purpose: '基于具体园区名称近两年发起过招标的企业列表查询' (query list of companies that initiated tenders in the past two years based on specific park name). It specifies the exact resource (park_issued_tender_company_list) and action (query), and distinguishes it from sibling chain_issued_tender_company_list (which is for chains) and the companion park_issued_tender_company_num (which returns count). The description also explicitly notes it returns a list, not a count.

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 clear usage scenarios with '典型问法' (typical queries) showing exactly how to use the tool (e.g., '中关村软件园近两年发起过招标的企业名单'). It explicitly states what is not included ('不包含：其他企业分类的统计；仅返回数量不返回名单'), which clarifies exclusions. However, it does not explicitly name alternative tools (like the chain variant) for when the user might want a chain instead of a park, though the park/chain distinction is implied by the name and the 'park' prefix.

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