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

Annotations only carry openWorldHint: true, so the description bears most of the behavioral disclosure burden. It adds useful context about scope (listed-company-only, specific metric coverage like 资产负债率, 销售利润率), but doesn't disclose behavioral traits such as pagination behavior, data freshness, open-world completeness caveats, or the cost implication of 200 credits/run despite that being relevant context for an agent.

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 well-structured into purpose, exclusions, and example questions, which aids scanning for an agent. However, the metric bullet list is somewhat long and could be trimmed since these largely overlap with user intent rather than parameter or behavioral specifics; every line roughly earns its place but the overall length is at the upper bound.

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 there's an output schema (Has output schema: true) and only 2 simple parameters, the description covers the key contextual bases: what data is included, what's explicitly excluded, pricing, and realistic user question patterns. This is reasonably complete for a modest-complexity query tool, lacking only minimal margin around edge behavioral details.

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%, covering both company_name and country_name with examples, which sets a baseline of 3. The description's example questions implicitly show parameter usage (e.g., 中国比亚迪股份有限公司应收账款周转率如何 maps to country+company), but it doesn't add notable syntax, format, or edge-case semantics beyond the schema beyond reinforcing the country+company pairing for cross-border queries.

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 first sentence uses a specific verb-resource pair (按企业查询经营活动方面的周期变化 for listed company financial indicators) with explicit scope. The description clearly distinguishes this from the many enterprise_change_* and chain_*/park_* siblings by specifying it covers revenue/profit, assets/liabilities, growth, and market cap for listed companies, backed by concrete metric examples.

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 explicitly states exclusions ('不用于非上市企业，也不用于生成完整财务报表' and '不包含：非本分类指标；按园区/产业链批量筛企业名单'), giving clear when-not-to-use signals. It falls just short of the top score because it doesn't name an explicit alternative sibling tool, though the examples ('典型问法') strengthen usage guidance.

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