Trace each step's necessity in a plan, detect broken links, cycles, and transitive waste, then output a simplified plan containing only required steps.
核心工具：追溯每个环节的必要性，产出精简方案 —— 哪些环节追溯不到目标（无用功）、哪些去掉确实没差别、哪些可以换成更轻的做法、哪些是真正必需的最短链条。判据只有一条：它连不连得到目标。成本只用来排序。
| Name | Required | Description | Default |
|---|---|---|---|
| by | No | ||
| plan | Yes | ||
| today | No | ||
| ledger | No | 可选：把判定记进这份台账 | |
| patterns | No | 无用功模式库路径；省略则不做模式匹配 |
Changes observed during successful MCP inspections.
v3.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
没有 annotations，描述承担了全部行为披露责任。它说明了分析逻辑和产出类别，但没有披露是否有副作用、是否写入 ledger、返回什么、是否只读。ledger 参数的存在暗示可能记录判定结果，但描述本身没有提及这一行为。
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?
描述通过破折号列出四类结果，并用一句话给出判据，结构清晰且没有空话。整体长度适中，信息密度高，但开头的'核心工具'标注更多是定位而非功能信息，略可精简。
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?
在无输出 schema、无 annotations、5 个参数且仅有 40% 覆盖率的条件下，描述没有足够支撑安全调用。缺少返回值说明、plan 的输入结构、ledger 写入副作用以及 pattern 匹配的触发条件，导致调用者仍需外部知识才能正确使用。
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 描述覆盖率只有 40%，而描述没有按参数名解释含义。它引入了'目标'和'成本'等概念，但并未映射到 plan、by、today 等参数；唯一的必填参数 plan 的内容和格式完全没有被解释。
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?
描述明确了核心动作：追溯每个环节的必要性并产出精简方案，并列出了四类具体输出（无用功、去掉无差别、换更轻做法、必需最短链）。它不是同义反复，且能被一个具体动词和资源所界定；不过它没有明确对比兄弟工具，因此不是满分。
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?
描述隐含了使用时机：当需要精简方案时，用'是否连得到目标'作为唯一判据，成本只用于排序。但它没有显式说明何时不该用、也没有点名替代工具（如 qhrisk_plan_check 或 qhrisk_recheck），使用边界靠推断。
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.