对两个零部件做「多 Agent 质保复核」：Worker 层执行标准四维兼容性裁决（与 /api/compatibility 同一引擎），Governor 层独立复核结论——按证据强度给出 L0–L3 风险分级、在证据不足 2 条时把"兼容"降级为"需人工确认"、对无法判定项显式列出缺失证据段。返回四维细节 + 证据契约 + governor_review。只读、免鉴权。
| Name | Required | Description | Default |
|---|---|---|---|
| component1_id | Yes | 零件 1 的 ID，形如 ACT-001 / CHIP-001 / PROTO-012。请先用 search_components 取得，不要自行拼造。 | |
| component2_id | Yes | 零件 2 的 ID，取值方式同 component1_id。两个 ID 可以属于不同品类。 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it states read-only and auth-free behavior ('只读、免鉴权'), the same engine as /api/compatibility, the downgrade rule at <2 evidence items, and explicit listing of missing evidence. No annotation contradiction exists.
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?
Four dense sentences with no filler; each clause adds a distinct fact: purpose, engine identity, governor behavior, return contract, and auth. The most important behavioral caveats are front-loaded.
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 2 parameters, no annotations, and no output schema, the description adequately covers safety, return summary, and logic. Minor gap: the four dimensions and evidence-contract structure are named but not detailed, and there is no explicit routing to simpler siblings.
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 coverage is 100% and the schema already documents ID format and the search_components prerequisite. The tool description itself adds no parameter-level detail, so the baseline of 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 opens with a specific action and resource: '对两个零部件做「多 Agent 质保复核」'. It differentiates itself from plain compatibility checks by describing the Worker/Governor layered review and L0–L3 risk grading, making it distinguishable from siblings like check_compatibility and bom_compatibility_check.
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?
It clearly frames the tool for high-assurance QA review scenarios ('质保复核', 'Governor 层独立复核结论'), so an agent can infer when a deeper audit is wanted. It does not explicitly name sibling alternatives or exclusions, but the context is clear enough for selection.
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.
多个工具处理重叠的任务：check_compatibility、review_compatibility 和 bom_compatibility_check 都涉及兼容性验证，其中前两个尤其相似，第二个使用了与第一个相同的引擎，可能是多余的。此外，search_components 和 semantic_search 重叠但具有不同机制。虽然这些描述有所澄清，但代理仍可能选择错误工具（例如，当简单检查就足够时使用了 review_compatibility）。
大多数名称遵循 verb_noun 模式（get_component_detail、search_components、review_compatibility），但有几个偏差：semantic_search 是 adjective_verb 而非 search_semantic，而 bom_compatibility_check 将操作放在最后，与 check_bom_compatibility 相反。模式的不一致性削弱了可预测性。
使用 9 个工具，组件覆盖了搜索、详情、参数语义、标准审计、推荐以及兼容性检查的多个变体——表面上足够广，但没有膨胀。每个工具针对不同的检索或分析需求，使其合理且可管理。
该表面涵盖了该领域的大部分关键功能：搜索、详情、语义标准化、标准审计、推荐以及通过三种模式进行的兼容性检查。缺失 CRUD 操作可能表明它是一个只读库，但没有任何接口来创建或更新部件，这限制了对数据库的管理。总体而言，对于查询和验证，覆盖范围相当完整，仅有边缘缺口。