audit_result

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

Annotations already signal a read-only operation, so the description adds useful behavior beyond that: it returns status values of 'present|missing|run' and suggested_function names for missing checks. It also indicates output scope ('every robustness check the literature expects'), giving the agent a clear expectation of payload content.

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?

Two sentences, front-loaded with the core purpose, followed by the essential input requirement and return behavior. Every clause earns its place; there is no filler or repetition of schema content.

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 rich input schema, output schema, and readOnlyHint annotation, the description covers what the agent needs to invoke the tool correctly: the required handle, how to obtain it, and what the response will contain. The optional parameters are adequately documented in the schema.

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 coverage is 100%, so the schema already documents all six parameters. The description adds workflow-critical meaning around result_id by instructing that it must come from an earlier call made with as_handle=true, which is not fully obvious from the schema alone.

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 verb ('audit'), a specific resource ('previously-fitted result'), and the required input ('result_id returned by an earlier tool call'). It distinguishes itself from a plain design audit by emphasizing that it operates on a fitted result and returns the same checklist sp.audit() produces with status flags and suggested functions.

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?

It gives an explicit precondition: pass the result_id produced by an earlier tool call with as_handle=true. This tells the agent when the tool can be invoked, though it does not explicitly name alternatives or state when not to use it (e.g., for a design not yet fitted).

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