company_competing基于明确指定的企业名称，查询该企业的竞品信息，包括竞品项目名称、竞品项目标签、最新融资轮次、成立时间、所属地、项目简介、所属企业、品牌介绍、联系电话、邮箱、官方网址、地址等。
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）。用于查询该企业的竞品信息。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 suggests external/real-world side effects, but the description neither explains this nor contradicts it, so no annotation contradiction. The description does add the credit-based pricing disclosure (0.2 credits/run), which is genuine behavioral context that warns agents of per-run cost. However, it doesn't discuss rate limits, data freshness, or the openWorldHint implication, leaving room for more transparency.
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 front-loads the core purpose in the first sentence and appends pricing in a clear block, which is good. However, the long comma-separated list of ~13 return fields is verbose and partially redundant given that an output schema exists and a complete field list would be documented there. Every sentence earns its place functionally, but the field enumeration could be more tightly pruned.
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 3-parameter tool with 100% schema coverage and a provided output schema, the description covers the essential ground: what it queries (competitor info by company name), the required parameter, pagination affordances, the output field families, and run cost. The description doesn't need to re-document return values because an output schema exists. Minor gaps include no clarification on the openWorldHint annotation's implications or whether the tool filters competitors by industry, but overall it's sufficiently complete for invocation.
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% — company_name, page, and limit each have clear Chinese descriptions, including an example value (通威股份有限公司) and pagination semantics. Per the baseline rule, high schema coverage earns a 3. The description's field enumeration does help clarify what company_name unlocks, but since the schema already documents all parameters well, the description adds little additional semantic value beyond that.
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 clear verb+resource statement ('基于明确指定的企业名称，查询该企业的竞品信息') and enumerates the returned fields (竞品项目名称、最新融资轮次、所属地、电话、邮箱、网址等), making the query-by-company-name function unambiguous. It distinguishes itself from sibling tools like company_basic_info and company_financing by focusing specifically on competitor/竞品 data. Slight deduction because it doesn't explicitly contrast with a sibling to sharpen the distinction.
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 usage context is implied rather than stated: the description implies 'use this when you need competitor information for a specified enterprise' through the company_name parameter and the field list. However, there is no explicit when-to-use/when-not-to-use guidance, no alternative tool names (e.g., company_data_search, company_basic_info), and no mention of ordering or filtering behavior beyond pagination. It's adequate for a straightforward lookup but leaves differentiation to inference.
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。