Check that each plan step has clear goals and serves a defined purpose. Plans without clear answers to who they serve and what happens if removed yield unreliable conclusions.
计划自检：目标判据是否写清、每个环节是否都回答了「它服务于谁」和「去掉它会怎样」。没通过自检的计划，判出来的结论不可信。
| Name | Required | Description | Default |
|---|---|---|---|
| plan | Yes | 计划 JSON 的路径 |
Changes observed during successful MCP inspections.
v3.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It conveys the check's purpose and a warning about unreliable conclusions, but it does not disclose whether the tool is read-only, what it returns, or whether it modifies the input plan. Key operational traits are missing, leaving the agent to guess about side effects and output behavior.
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, readable sentence. The main action and resource are front-loaded ('计划自检'), followed by the specific criteria and a consequence. Every clause carries meaning, and there is no redundant or filler wording.
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?
With one parameter, no output schema, and no annotations, the description must explain both invocation and interpretation. It explains the check criteria and warns about consequences, but it never states what the tool returns (e.g., pass/fail, issue list) or whether the plan file is altered. For an agent to correctly call and use the tool, this missing return-value and side-effect information is a significant gap.
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 fully documents the single parameter 'plan' as '计划 JSON 的路径' (path of plan JSON), so schema coverage is 100%. The description adds no extra parameter-level details, which aligns with the baseline score of 3 when the schema already handles parameter semantics.
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 uses a specific verb ('自检' / self-check) and resource ('计划' / plan), and enumerates concrete check criteria: whether target criteria are clearly written, and whether each step answers 'who it serves' and 'what would happen without it'. This distinguishes it from sibling tools like qhrisk_review or qhrisk_mistakes, which appear to serve different review or error-analysis purposes.
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 this tool should be used before relying on a plan, by warning that plans failing the self-check yield untrustworthy conclusions. However, it does not explicitly state when to use this tool versus siblings such as qhrisk_review, nor does it provide when-not-to-use guidance. The usage context is present but left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.