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

The description explicitly discloses that the tool only returns a count and not a list, which is valuable behavioral transparency. It also notes what is not included (other company classifications). However, this disclosure conflicts with the tool's name, which reduces clarity, and no additional behavioral details like performance or permissions are mentioned. The annotation openWorldHint is present, but the description adds some useful caveats.

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, uses bullet points for exclusions, and includes three example queries. It is appropriately front-loaded with the main purpose, though the contradiction mars the flow. Overall, it is efficient with no wasted words, earning a 4.

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?

Given the tool's complexity (two params, one optional) and the presence of an output schema, the description lacks clarification on how the 'year' parameter relates to the '近两年' (last two years) window. The internal contradiction between list vs count also leaves the actual return format ambiguous. The description fails to fully clarify its own semantics, making it incomplete for reliable use.

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?

The input schema has 100% coverage with clear descriptions for both parameters, so the baseline of 3 is appropriate. The description does not add new parameter-specific semantics but uses examples that subtly imply the 'year' parameter is optional and likely represents a reference year for the two-year window. This is insufficient to raise the score, but does not lower it either.

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 it lists companies that won tenders in the last two years for a specific park, but then contradicts itself by saying '仅返回数量不返回名单' (only returns count, not name list). This directly contradicts the tool name 'park_won_tender_company_list' and makes the purpose unclear and misleading.

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 gives typical example queries, which suggests when to use the tool (e.g., '中关村软件园近两年有中标的企业名单'). However, it fails to distinguish this tool from the sibling 'park_won_tender_company_num' which likely serves the count-only functionality that this description claims. No explicit 'when not to use' guidance is provided, despite the internal contradiction.

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