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

With only { openWorldHint: true } in annotations, the description carries the disclosure burden and rises to the occasion. It transparently discloses the included indicator taxonomy (市场占有率；广告营销投入；广告到达率；品牌知晓率), explicitly excludes non-category indicators, and clarifies this tool does not support park/industry-chain bulk filtering. The 包含/不包含 structure effectively communicates scope boundaries that an agent could not infer from the sparse annotation alone. Minor deduction for not addressing output volume, pagination, or historical depth of the 'periodic change' data.

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 excellently structured with clear visual demarcation: purpose statement, explicit negative scope, a clean indicator list, exclusions list, and illustrative examples. Every section earns its place—there's no filler. Minor deduction for slight redundancy: 市场占有率和广告到达率 appear in both the intro sentence and the indicator list, and the text is on the longer side even though justified by the crowded sibling family of 160+ enterprise_change_* tools.

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 knowledge-query tool with a well-covered schema and an output schema present, the description covers all essential operational aspects: what to query, exact metric taxonomy, what's excluded, and how to phrase queries. Given that the sibling family includes many similar enterprise_change_* indicators (satisfaction, reputation_awareness, reputation_favorability, capital_brand_*), the description's explicit boundary-setting adds real completeness. A small gap exists around time-range/periodicity semantics of '周期变化', but this is minor given the output schema 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?

The input schema already documents both parameters well with examples (company_name: 「比亚迪股份有限公司」「Tesla, Inc.」; country_name: 「中国」「美国」「Japan」「China」), so schema coverage is 100%. The description adds marginal value by showing realistic parameter combinations in the typical-questions section (e.g., '中国比亚迪股份有限公司市场占有率' demonstrates the {country}+{company}+{metric} pattern implicitly). However, this is enrichment of usage rather than new parameter semantics—the schema already handles the documentation job.

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 precise verb+resource+scope statement: '按企业查询用户品牌方面的周期变化' (query periodic brand changes by company), then enumerates exact indicators covered (market share, ad investment, ad reach, brand awareness). It explicitly differentiates from the sibling tool enterprise_change_user_brand_satisfaction by disclaiming satisfaction metrics (客户满意度、投诉率) and reputation evaluation (舆情口碑美誉评价), which is critical given the near-identical sibling tool.

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 explicit when-not-to-use guidance via double-negative framing: '不用于客户满意度、投诉率等满意度指标，也不用于舆情口碑美誉评价' and '不包含：非本分类指标；按园区/产业链批量筛企业名单'. It also gives three realistic usage examples showing the expected query pattern (country + company + metric). However, it stops short of naming alternative sibling tools explicitly (e.g., 'use enterprise_change_user_brand_satisfaction for satisfaction metrics'), which would earn a perfect 5.

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