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

With only openWorldHint=true as annotation, the description carries most of the burden. It does add value by enumerating the 12 metric categories covered and explicitly listing exclusions, which sets expectations about breadth. It also discloses per-run pricing and includes realistic usage examples. However, it stays silent on practical behaviors like result freshness windows, output volume caps, or any constraints that would apply when many metrics are requested. No contradiction with the openWorldHint annotation.

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?

Despite being fairly long, the description is well-structured: a lead sentence with purpose, explicit exclusions, a bulleted list of covered metrics, a formal 'not included' line, and three example queries. Each section serves a purpose for a Chinese business-research context. The only quibble is some redundancy between the 'not for' and 'not included' sections, but the structure earns its place for the tool's complexity.

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 simple 2-parameter tool with full parameter coupling (both required), the description is essentially complete: parameters are fully documented, the metric scope is explicit, pricing is set, and an output schema exists to cover returns. The description is sufficient for an agent to both identify the right time to call this tool and avoid mis-firing on sibling tools like enterprise_change_company_profile or the generic enterprise_change_competitor_moves queries. The only missing aspect is why this sits alongside 50+ siblings for the same company, but that's a catalog-wide concern, not a gap in this description.

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% — both company_name and country_name have Chinese descriptions with concrete examples in the 'typical questions' and param docs. The description reinforces that an exact/full enterprise name is needed ('基于具体企业名称'), which is marginally useful. However, it doesn't add further parameter-level semantics such as whether the name needs to be legally registered, whether suffixes matter, or any format/transliteration rules. With high schema coverage, baseline 3 is appropriate, but the description adds little beyond what the schema already conveys.

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 verb+resource+scope: query business activity cycles for a specific named company ('按企业查询经营活动方面的周期变化'), focused on product-related topics. It provides strong positive scope (product layout, market performance, supply risk, tech disruption) and includes negative scope (not for product-name search across all enterprises). However, it does not name any of the ~50 enterprise_change_* siblings for differentiation, even where overlap is likely (e.g., enterprise_change_competitor_moves).

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 explicit usage context including exclusions ('不用于按产品名称检索全市场企业，也不替代竞争对手动向专项查询'), a formal 'not included' section (non-classified metrics, park/industry chain batch filtering), and three typical question examples. It clearly signals prerequisites (specific full enterprise name) and boundary conditions. It stops short of a 5 because it never cites sibling tool names, forcing the agent to infer the alternative from description alone, and one example ('what competitors does Tesla have') seems to overlap with the sibling enterprise_change_competitor_moves without clarification.

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