company_salary基于明确指定的企业名称，查询该企业的工资待遇信息，包括平均工资、同地区比例、同行业比例、对比去年、最多人拿等。
Pricing: {"unit": "credits", "billing_model": "per_run", "per_run": 0.2}
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 指定返回第几页结果，从 1 开始，默认 1；与 limit 配合使用。 | |
| limit | No | 指定单次请求最多返回的记录数，默认 20，最大 100。 | |
| company_name | Yes | 企业名称（必填）。用于查询该企业的工资待遇分析信息。示例：通威股份有限公司 |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation openWorldHint: true is provided, but the description does not add behavioral context beyond the basic query function. It doesn't mention whether the tool is readonly (though it likely is), any rate limits or pricing (though pricing is included in the description but that's not behavioral), or what happens if the company is not found. The description does not contradict the annotation, but it also doesn't add meaningful transparency beyond what's obvious from the schema.
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 concise (one sentence plus a pricing note) and front-loaded with the core purpose. It efficiently lists the key output dimensions in a single breath. The pricing information is relevant but could be considered extraneous to the tool's functional description, yet it adds value for cost-aware agents. No redundancy with the schema.
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?
The tool has a simple input schema and an output schema is present (though not shown). The description covers the main output concepts. However, it does not mention edge cases like what if the company has no salary data or how pagination works beyond the schema defaults. Given the tool's moderate complexity, the description is adequate but not comprehensive.
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 covers 100% of the 3 parameters with detailed descriptions for each (company_name with example, page with default, limit with default and max). The description adds a high-level summary of the output fields but does not elaborate on parameter usage beyond what the schema already provides. Baseline 3 is appropriate since schema coverage is complete.
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 tool queries salary information for a specified company, including average salary, regional/industry comparisons, year-over-year changes, and the most common salary range. This distinguishes it from sibling tools that focus on other company attributes (e.g., patents, shareholders, tenders). However, it could be more explicit about what makes this different from other company query tools, though the salary focus is distinctive.
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 implies usage: when a user wants salary information for a specific company. It specifies the company name must be provided. However, it does not explain when NOT to use it (e.g., when searching without a known company name, or when other tools might be more appropriate for broader company analysis). The sibling list is extensive but no alternative tools are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
大量工具功能高度重叠，例如chain_*和park_*系列均为按不同筛选条件查询企业列表或数量，只是参数不同却拆分为独立工具；enterprise_change_*系列同样针对不同指标逐一拆分。虽然描述清楚各自区别，但代理面对198个工具时极易选错，且许多工具本质应合并为带参数的单一接口。
多数工具采用snake_case加领域前缀（如chain_、park_、company_、gov_data_、poi_data_），但存在明显变体如company_certlist、company_randomin_spection（拼写异常）、corporate_exception_report、due_diligence_report、sg_chokepoint等，混用英文抽象名词与动词短语，整体模式可辨认但不统一。
工具总数高达198个，远超合理范围（即使复杂领域也应控制在25个以内）。大量工具是同一逻辑的不同参数变体（如list/num、不同资质条件），完全可以通过参数化减少数量，严重冗余，代理难以有效浏览和选择。
工具覆盖领域广泛，包括企业信息、产业链分析、园区统计、地区宏观、POI明细、供应链风险、关税计算等，基本覆盖了商业数据查询的主要需求。虽缺少更新/删除等操作（但作为查询服务器可接受），且部分细分领域可能有遗漏，但整体功能较为完整。