品质管理全生命周期系统：按丰田源头品质方法生成企划→研发→生产准备→号试→量产六阶段全套品质文档（QFD、DFMEA、控制计划等）。
Args:
company: 企业名称。
product_type: 产品类别，例如「注塑件」「电机」。
module: 只生成某一模块时填 Q1–Q12，全部生成填 ALL（默认）。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| module | No | ALL | |
| company | No | ||
| license_key | No | ||
| product_type | No | ||
| payment_proof | 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?
No annotations are provided, so the description carries the full burden, and it does disclose important behavior: the first call is payment-gated and returns payment instructions, and a license_key bypasses payment. It omits details like idempotency, timing, or what happens if an invalid proof/license is supplied.
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?
Front-loaded one-line purpose followed by a compact Args block; every entry adds information rather than restating the schema. Sized appropriately for a tool at this complexity.
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?
An output schema exists, so return values need not be described, and the description adequately covers the payment gating, license alternative, and module scoping. The main residual gap is the unexplained Q1–Q12 module taxonomy, which an agent would need in order to target a specific module.
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?
With 0% schema description coverage, the description must compensate and does: it documents all five parameters, including the payment-or-license mutual-exclusion rule and the ALL/Q1–Q12 module switch. It never explains what modules Q1–Q12 actually correspond to, leaving that opaque.
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?
States a specific verb and resource ('生成...品质文档') plus concrete scope: six stages and named deliverables (QFD, DFMEA, 控制计划). It is clearly distinguishable from the sibling tools, but it never explicitly contrasts itself with any of them, so it falls 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?
Gives strong in-tool workflow guidance: how to select a single module (Q1–Q12) versus ALL, and a full payment/licensing flow (leave payment_proof empty on first call, retry after payment, or supply license_key). It does not address when to prefer this tool over siblings like manufacturing_analytics or cost_improvement.
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.