audit_file

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool is non-blocking ('不阻断') and returns structured results ('返回结构化结果'), which are useful behavioral traits. However, it doesn't mention side effects (e.g., whether it modifies anything), permissions, or the exact structure of the return. For an audit tool, the non-blocking and structured-result info is helpful but not comprehensive.

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, compact sentence that front-loads the core purpose and key behavioral notes (non-blocking, structured results). There is no wasted text; every clause earns its place. This is highly concise and well-structured.

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 relatively simple tool with 4 parameters, full schema coverage, and no output schema, the description covers the essential usage context: when to call, what it does, and the non-blocking nature. It doesn't describe the output format in detail, but since there's no output schema, some guidance might be expected. However, for an audit tool, the structured result is implied to be a standard response. Overall, adequate for correct invocation, though a bit more detail on the return would elevate 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 fully documents all four parameters. The description adds no additional parameter semantics beyond what the schema already provides (e.g., diff for content-level rules, task for context rules are already in the schema). At baseline 3, since the schema does the heavy lifting and the description doesn't compensate further.

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 states a specific action ('审计' - audit) on a specific resource ('单文件变更' - single-file change), and clarifies the trigger context ('Agent 编辑文件时调用'). It differentiates from siblings like run_audit or audit_data_change by emphasizing '单文件' (single file), though it doesn't explicitly name alternatives. Clear but not fully differentiated.

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?

Provides a clear trigger condition ('Agent 编辑文件时调用') and scope ('跑单文件适用规则'), indicating it's for single-file edits. However, it doesn't explicitly state when NOT to use it or mention alternative tools, so it lacks explicit exclusions. Clear context, no alternatives mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.