判断一项 AI 服务要办哪些手续（备案/安全评估/标识），逐条给出法规依据。
Args:
public_facing: 是否面向中国境内公众提供服务（仅内部使用请传 false）
generates_content: 是否能生成文本/图片/音频/视频等内容
edits_face_or_voice: 是否提供人脸、人声等生物识别信息编辑功能（换脸、AI 配音、数字人）
only_internal_use: 是否仅企业内部使用、不对外提供
| Name | Required | Description | Default |
|---|---|---|---|
| public_facing | No | ||
| generates_content | No | ||
| only_internal_use | No | ||
| edits_face_or_voice | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds that the tool returns legal-basis citations item by item, which clarifies the output behavior. There is no contradiction with annotations, and the tool is clearly an advisory/judgment operation rather than a mutating one.
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 compact and front-loaded: one purpose sentence followed by parameter explanations. Every line adds needed information—purpose, output behavior, and parameter semantics—with no filler or redundancy.
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 decision tool with four boolean inputs and an output schema, the description covers purpose, parameter semantics, and output style. The main gaps are the lack of explicit sibling-tool routing and guidance on how conflicting parameters (e.g., public_facing vs only_internal_use) should be interpreted.
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 0%, so the description carries the full semantic burden for all four boolean parameters. It explains each parameter in plain language with practical examples (换脸、AI配音、数字人), making the intended values and distinctions clear.
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's purpose: determining which AI-service compliance procedures (备案/安全评估/标识) apply and providing legal basis item by item. It uses a specific verb, identifies the resource, and lists concrete procedure types, though it does not explicitly distinguish itself from sibling tools.
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 explicit: use this tool when you need to determine filing/compliance requirements for an AI service. The description does not state when to prefer it over sibling tools like self_check or search_compliance, nor does it give exclusion criteria.
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.