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

With annotations limited to openWorldHint:true, the description carries the burden, and it delivers by exhaustively enumerating the in-scope indicators (应收账款周转率, 营业收入, 增长率, 杠杆率, 利润总额, etc.) and out-of-scope actions (batch list screening, full report generation). It does not disclose data sources, update frequency, or how real-time the market-cap/stock-price portion is, which prevents a perfect score.

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 long but deliberately structured with scannable sections for included indicators (涉及指标), exclusions (不包含), and typical questions (典型问法). Every sentence contributes to disambiguating among the many similar enterprise_change_* siblings; the organization keeps the length acceptable, though it leans toward completeness over brevity.

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 an output schema exists, not explaining return values is correct per the rubric. The description covers purpose, applicable subjects (listed companies), a full indicator checklist, exclusions, and worked examples. The one notable gap is lack of clarification on the temporal behavior of '周期变化' and stock-price/quote data (e.g., real-time vs. historical), but overall it's well-rounded.

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 coverage is 100% since both company_name and country_name already contain inline examples (比亚迪/Tesla and 中国/美国/Japan). The description's typical questions reinforce the full-name-plus-country-prefix convention (e.g., '中国比亚迪股份有限公司'), adding marginal value, but this is baseline territory given the schema already fully documents both parameters.

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 opens with a specific verb+resource construction ('基于具体企业名称，按企业查询经营活动方面的周期变化') and precisely scopes the tool to listed companies' financial metrics (营收利润、资产负债、成长性、市值与股价走势). It further disambiguates from the many sibling tools by spelling out the included indicators and adding three realistic example questions (BYD, Tesla, Toyota), leaving no doubt what this tool does.

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?

Provides explicit when-to-use framing ('用于查询上市企业...') and clear 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'). These exclusions map to alternative tool categories (e.g., park_*/chain_* list tools), though no sibling tool is mentioned by name.

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