Audit a git diff against 25 rules and produce a structured report for commit-time governance, with task, silent, and strict options.
对 git diff 运行全量审计（25 条规则），返回结构化审计报告。
| Name | Required | Description | Default |
|---|---|---|---|
| diff | No | git diff 范围（如 HEAD~1..HEAD）。默认 HEAD~1..HEAD | HEAD~1..HEAD |
| task | No | 任务描述（用于 A3 不改越界检查） | |
| silent | No | 沉默模式：跳过日志依赖规则，走 diff 启发式回退 | |
| strict | No | 严格模式：无日志时 A7/A8 返回 FAIL 而非 WARN |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, yet it only says the tool audits and returns a report. It does not say whether the operation is read-only, whether it needs a git repo/working directory, what happens on rule failure, or how errors surface. The 'structured report' mention is the only behavioral signal.
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?
A single dense sentence with the action and scope front-loaded and no filler. Nothing in it is redundant.
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?
For a 4-parameter tool with no output schema and no annotations, the description is minimally adequate: it states the audit runs 25 rules and returns a report. It omits what the report contains, how failures are represented, and any prerequisites, leaving real gaps for an agent deciding how to call it.
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 description coverage is 100%, so the schema already explains diff, task, silent, and strict. The description adds only the '25 rules / full audit' framing and does not clarify the default diff range or the silent/strict semantics beyond what the schema states. Baseline 3 applies when the schema does the heavy lifting.
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?
Names a specific verb (run a full audit), a specific resource (git diff), and a scope (25 rules) plus the output form (structured report). It is distinguishable from audit_file/audit_data_change by targeting a git diff, but the description never explicitly separates itself from the many other audit* siblings, so it stops 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?
There is no statement of when to use this versus audit_file, audit_data_change, or audit_query. The silent/strict modes exist in the schema but the description gives no guidance on when a caller should reach for them. Only implied usage is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.