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

Annotations are minimal (only openWorldHint: true), so the description carries the behavioral disclosure burden. It states that results are combined text of multiple list types, excludes other classifications, and explicitly notes it returns lists not counts. It also includes pricing information (100 credits per run), which is an additional behavioral detail not covered by 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 reasonably concise, with a clear primary statement followed by included types, exclusions, typical questions, and pricing. It is structured with line breaks for readability, but contains some redundancy (e.g., the '涉及指标/类型' line repeats the types already mentioned). Overall, it is efficient and front-loaded with the core purpose.

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 list-returning tool with an output schema present, the description adequately covers the scope, exclusions, and usage examples. It mentions the combined result format, specifies the region and chain filters, and clearly states what it does not cover (other classifications and count-only). No critical information is missing for an agent to decide appropriate 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?

Schema description coverage is 100% for all three parameters (year, region, chain_name). The description adds value beyond the schema by providing concrete example queries (e.g., '2024年全国集成电路高新技术企业名单') that illustrate how to format region, chain_name, and year together. This helps an agent understand parameter composition beyond trivial field descriptions.

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 that this tool queries high-tech company lists based on specific regions (country, province, city, district) and specific industry chain names, and returns combined text for total/production/sales/dependent types. It explicitly lists included types, excludes other classifications, and provides typical query examples. This distinguishes it from the sibling tool chain_high_tech_company_num, which likely returns counts, and other chain_*_company_list variants.

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 implicitly differentiates usage by stating '不包含：仅返回数量不返回名单' (excludes: only count, not list), which indicates this tool is for lists and not for counts. It also provides typical questions showing when to use it. However, it does not explicitly name alternative tools like chain_high_tech_company_num, leaving some ambiguity about direct comparison.

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