audit_api_contract

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

Annotations declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, and the description does not contradict them. It adds valuable behavioral context: the tool runs adversarial queries, returns specific verdicts, and catches shape-valid but wrong responses. This enhances transparency beyond annotations.

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 (two sentences) and front-loaded with the core action. However, it could be more structured by briefly covering key parameters or output, but overall it is efficient without waste.

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 complex schema (nested objects) and no output schema, the description is incomplete. It does not explain the verdict meanings, how to interpret results, or provide any error-handling context. Missing details about expected_shape_schema structure or query limits.

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 input schema has 0% description coverage, and the description does not explain the parameters (endpoint_url, queries, expected_shape_schema) beyond a high-level mention. The complex nested objects (queries array, expected_shape_schema) lack any textual guidance on their structure or usage.

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 is specific: it states the tool runs adversarial queries against a live endpoint and returns per-query verdicts (shape-valid, shape-invalid, confident-wrong, uncertain). It clearly distinguishes from siblings by focusing on catching shape-valid but wrong responses, a unique capability.

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 implicitly suggests using the tool for adversarial API testing but provides no explicit guidance on when to choose this tool over alternatives like audit_contract or audit_parity. No exclusions or context are given.

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