Identify plan simplification mistakes by tracing step necessity, detecting false deletions and false retentions, and categorizing items as required or pointless.
两种错法：虚删（判无用功删掉、后来发现它其实有用）与虚留（判必需保留、后来一次没用上）。后者是最沉默的错误 —— 没有任何机制会提醒你「你保留的这件事从没起过作用」。
| Name | Required | Description | Default |
|---|---|---|---|
| ledger | Yes |
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 full responsibility for disclosing behavior. It only discusses the concept of silent mistakes and says nothing about side effects, return values, how the ledger is processed, or whether the operation is a read, analysis, or report.
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 prose is short, front-loaded, and stylistically sharp, with no filler sentences. However, the compactness comes at the expense of operational information, so this is closer to under-specification than to effective tool-description concision.
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 no annotations, no output schema, and a required `ledger` parameter, the description should explain the tool's role in the risk-review workflow and the expected ledger input. It does neither, so the agent has no complete basis for selecting or invoking this tool rather than siblings like qhrisk_review or qhrisk_ledger_check.
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 single required parameter `ledger` has zero schema description coverage, and the tool description never mentions it. An agent cannot determine what format or content is expected for `ledger` or how it relates to the two mistake types.
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 defines '虚删' and '虚留' as mistake categories but never states an action or resource: it does not say that the tool checks, classifies, or reports mistakes in a ledger. It resembles a topical gloss on the name 'qhrisk_mistakes' rather than an operational definition, and it does not distinguish itself from siblings like qhrisk_ledger_check or qhrisk_review.
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?
No guidance is given about when to call this tool or when to prefer alternatives. The text explains an error taxonomy but provides no invocation condition, workflow context, or criteria for choosing this tool over the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.