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

The description goes beyond the sole annotation (openWorldHint: true) by specifying that it returns only a list, not counts, and does not include other company category statistics. This clarifies response behavior. It also includes pricing information in the description, which is behavioral context. The openWorldHint annotation indicates the tool may require external knowledge (e.g., park names), and the description provides example park names, which complements it. No contradiction with 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 description is compact, front-loaded with the purpose, and uses bullet-like structure for exclusions and examples. The typical question examples are valuable for an AI agent. It is not overly verbose, though the pricing block is slightly extraneous but acceptable as metadata. It earns a high score for being structured and concise.

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?

The tool has only 2 parameters (one required, one optional), an output schema exists (not shown but indicated), and annotations are minimal. The description provides enough context: what it returns (list), what it excludes, and examples. It lacks explicit mention of the output format (e.g., fields in the list), but the output schema likely covers that. Given the modest complexity, this is adequately complete, with slight room for more explicit boundary conditions (e.g., what if no data exists).

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%, with both parameters (park_name and year) having descriptions. The description adds typical question examples and clarifies the year is optional (implied by '近两年' but the schema says '统计年份，如 2024；可选。'). Beyond that, it doesn't add deeper semantics such as format constraints or relationships between parameters. The base score of 3 is appropriate as the schema does the heavy lifting.

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 a list of companies that won tenders in the past two years based on a specific park name. It explicitly mentions the metric/type, what is excluded (statistics for other company categories, returning only counts), and provides typical question examples. This distinguishes it from sibling tools like park_won_tender_company_num (which returns counts) and other park_*_list tools that query different company categories.

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 concrete typical question examples ('典型问法'), which implicitly guides when to use this tool. It also clarifies that it returns a list, not just counts, and does not include other categories. However, it does not explicitly mention when to use alternative tools like park_won_tender_company_num for counts, nor does it state exclusion criteria like 'use this instead of X'. The clear examples and scope notes are nevertheless strong guidance.

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