company_punish基于明确指定的企业名称，查询该企业受到的行政处罚记录，包括决定文书号、决定日期、行政处罚种类、决定机关、处罚事由、处罚结果等。
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）。用于查询该企业的行政处罚。示例：通威股份有限公司 |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include only openWorldHint=true, providing minimal context. The description discloses that it returns a list of penalty records with specified fields, and includes pricing information, which is useful for cost awareness. It does not, however, mention pagination behavior or any potential gaps in data, but the schema covers pagination parameters, so the description is adequate given the annotation coverage.
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, with a clear first sentence stating purpose and output fields. The supplementary pricing line adds valuable cost information without bloat. Each sentence earns its place, and the structure is front-loaded with the core function.
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 the tool's complexity is moderate (one required parameter, pagination details in schema, and an output schema exists), the description provides sufficient context. It enumerates the data fields returned, covers all required inputs implicitly, and notes pricing. It does not explain the output schema, but that is unnecessary since it exists. It could mention the presence of pagination explicitly, but that is captured in the schema, so it is not a critical gap.
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%, and the description mentions the required company_name and lists the returned data fields. It does not add semantics beyond the schema for page and limit, but the schema already provides clear descriptions. The tool name and description reinforce the parameter's purpose, so baseline 3 is appropriate.
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 explicitly states it queries administrative penalty records for a specified company, enumerating the returned fields (decision document number, date, type, authority, reason, result). It is clear and distinct from sibling tools, which cover other company attributes (e.g., basic info, patents, violations).
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 states that the query is based on a clearly specified company name, implying it should be used when needing penalty records for one company. However, it does not explicitly state when not to use it or mention alternative tools (e.g., company_illegal for broader violations). It lacks explicit exclusions or comparisons with siblings.
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.
Most tools have clearly distinct purposes, with consistent scopes (e.g., chain_* vs park_* vs company_* vs gov_data_*). The list/num pairs are clearly differentiated. A few overlapping concepts exist (e.g., company_patent vs enterprise_change_innovation) but descriptions clarify the angle. Some typos (company_randomin_spection) don't cause ambiguity.
Naming follows a mostly predictable snake_case pattern with prefixes indicating domain (chain_, park_, company_, enterprise_change_, gov_data_, poi_data_, business_surrounding_, cbd_surrounding_). Most tools use <prefix>_<entity>_<action> or <prefix>_<subject>. A few outliers (sg_chokepoint, tariff_calc, corporate_exception_report) deviate but are few and recognizable.
With 198 tools, this is far beyond any reasonable scope for a single server. It exceeds even the 'extreme mismatch' threshold of 50+ tools. The large number makes selection and discoverability challenging, despite good internal organization.
The tool surface covers a vast range of enterprise data, regional macro stats, POI details, supply chain analysis, and tariffs. It appears to cover the primary domain comprehensively, with only minor potential gaps (e.g., no direct tool for company debt ratings or specific product catalogs, but these are addressed via enterprise_change_* and company_* tools).