audit

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It states the tool verifies or stress-tests work but does not mention any side effects, state modifications, or output characteristics. Given an output schema exists, the description should at least hint at return values or logging behavior. The transparency is insufficient.

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 concise and well-structured: first a clear purpose statement, then a list of actions, then parameter descriptions. It wastes no words and front-loads the key use case. Some details could be added without harming conciseness, but as is, it is efficient.

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?

Given the tool has 4 parameters, a nested object, an output schema, and many sibling tools with similar actions, the description is incomplete. It does not explain what each action does, nor describe the output or provide examples. The agent would need to infer or look up sibling tools to fully understand usage. More completeness is needed for safe invocation.

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 description adds meaning to parameters: action is described as 'which audit to run' with a list of possible values; subject is explained as 'what is being audited (decision, code, plan text)'; depth is specified as recursion depth for certain actions. However, context is only vaguely described as 'Action-specific parameters,' leaving a gap. Overall, it adds moderate semantic value beyond the schema, which has 0% description coverage.

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 clearly states that the tool is used to verify or stress-test work before committing, with a specific use case of being used before decisions, code, or plans. It lists possible actions, which helps define its scope. However, it does not differentiate from sibling tools that perform similar individual audits, leaving ambiguity about when to use this meta-tool vs. specific audit tools.

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 provides some usage guidance by stating 'Use before decisions, code, or plans,' which indicates when to invoke the tool. However, it lacks explicit when-not-to-use scenarios or comparisons to alternatives. With many sibling tools for specific audits, the agent would benefit from guidance on preferring this tool over individual actions.

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