中国 AI 合规与备案（条文级自查）

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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds the behavioral detail that the tool returns a composite of four content sections, which is useful context beyond the annotations. It does not describe error behavior or what happens with an invalid slug, but that is a minor gap 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 compact and front-loaded: the first sentence states the purpose and return contents, and the Args section is a single line that gives the parameter semantics. Every sentence earns its place; there is no filler.

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 single-parameter read-only retrieval tool with an output schema present, the description is nearly complete. It explains what the tool returns, how to get the required parameter, and the annotations cover safety. The only missing piece is explicit error behavior for an invalid slug, but that is not essential for an agent to call the tool correctly.

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 must compensate. It does: it explains that slug is a '条目标识' and tells the agent how to obtain it (via list_topics or search_compliance). This adds real meaning beyond the bare schema property name 'slug'.

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 states a specific verb ('取一条'), a specific resource ('合规要求的完整内容'), and enumerates the content components (正文 + 依据条文 + 落地动作 + 常见追问). It clearly distinguishes this from sibling tools like list_topics and search_compliance, which are about discovery rather than retrieval of a single item.

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 context: it is for fetching a single requirement by slug, and it explicitly tells the agent to first use list_topics or search_compliance to obtain the slug. It does not explicitly state when not to use it or name alternatives, but the prerequisite guidance is clear and actionable.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful context by stating the tool lists all compliance-entry titles and by spelling out the cluster filter values, which goes beyond the annotation metadata without contradicting it.

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: one clear purpose sentence plus a tight Args block. Every line adds either the tool's outcome or the parameter vocabulary, and there is 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?

This is a simple read-only list tool with one optional parameter and an output schema, so the description does not need to explain return values. It supplies the filter domain and scope needed to invoke the tool correctly; a brief pointer to sibling tools would improve it but is not essential here.

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 must compensate for the sole parameter. It explains that cluster filters by cluster and enumerates all meaningful allowed values with Chinese labels. It could be more explicit that an empty default means 'no filtering', but the optional tag plus default value make this reasonably 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 action ('列出') and resource ('全部合规条目的标题清单'), so an agent knows this tool returns a list of compliance-entry titles. However, it does not explicitly differentiate itself from siblings like search_compliance or get_requirement, so it stops short of a 5.

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 only usage hint is that cluster is an optional filter with named values. There is no guidance about when to choose list_topics versus search_compliance, get_requirement, or other sibling tools, and no when-not-to-use guidance is provided.

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

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds detail about the returned content but no additional behavioral context such as pagination, access requirements, or rate limits; it does not contradict the annotations.

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 a single, compact sentence that front-loads the main action and packs the returned fields into a parenthetical. Every word contributes, with no redundancy or filler.

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 zero-parameter, read-only catalog tool with an output schema and strong annotations, the description is complete: it names the operation and the data fields returned. Nothing essential is missing for an agent to invoke it correctly.

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 tool has zero parameters, so the baseline of 4 applies. With no parameters to document, the description does not need to explain parameter semantics, and the schema coverage is trivially 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 retrieves a catalog of included regulations ('获取收录法规清单') and lists the fields returned. It is specific and can be distinguished from siblings like search_compliance or get_requirement by its focus on the full list, but it does not explicitly contrast itself with those 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?

There is no guidance on when to use this tool versus the sibling tools, no exclusions, and no prerequisites. The description only explains what the tool does, leaving the selection decision entirely to inference.

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

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

注释已声明readOnlyHint=true、idempotentHint=true、destructiveHint=false，描述了只读安全属性。描述额外补充了返回内容（含结论与条文依据），但对具体返回格式、分页或限制等未提供更多行为细节，符合有注释时的较低要求。

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?

描述简洁，两句话加Args列表，无冗余，关键信息（检索对象、返回内容）前置，结构清晰高效。

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?

有输出模式，无需说明返回结构；参数简单且有描述。虽缺少使用场景指导，但整体对于搜索类工具已足够，符合复杂度要求。

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描述覆盖率为0%，描述通过Args部分对query和top_k提供了具体解释，包括query示例和top_k默认值，补偿了schema缺失，但未提供参数格式限制或更多语义，故给4分。

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?

描述明确说明'按关键词检索中国 AI 合规条目'，动词'检索'加资源'AI合规条目'，并说明返回内容（含结论与条文依据），与兄弟工具（filing_route、get_requirement等）功能差异明显，目的清晰且可区分。

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?

描述未提供任何使用时机或与替代工具的对比，未说明何时应使用此工具而非其他兄弟工具（如regulation_info、list_topics），也无线索表明其适用场景或排除条件。

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

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that matching entries are filtered and their '落地动作' are aggregated into a checklist, but it does not discuss error handling, rate limits, or other edge-case behavior. There is no contradiction with the annotations.

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 one focused purpose sentence followed by a compact parameter explanation with examples. It is front-loaded, contains no filler, and avoids repeating schema-only details.

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 single-optional-parameter tool with annotations and an output schema, the description covers purpose, scope semantics, and default behavior well. It does not position itself against sibling tools, but that is a minor gap for basic 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?

The input schema only provides the parameter name, type, and default, so the description carries the full semantic burden. The Args block defines scope as a scenario or keyword, gives concrete examples, and documents the empty-string default, fully compensating for the 0% schema description coverage.

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 a specific purpose: generate scenario-based compliance self-check lists by aggregating matching items into checkable todos and listing legal bases. It is specific about the output and gives example scopes, but it does not explicitly distinguish itself from sibling tools like search_compliance or get_requirement.

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 when to use the tool through '按场景出合规自查清单' and provides example scope values, plus the blank-for-full behavior. However, it does not mention alternatives or state when not to use this tool, so routing between siblings is left to inference.

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