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

This is a model disclosure. It explains that a one-shot review machine is spawned, that it reads the checkout offline, that findings land on the Legal page, that no code change is applied automatically, and that the result carries a disclaimer_md field. It also discloses billing, one-review-per-project concurrency, 409-shaped refusals without a compliance profile, ok:false refusals with next_step, and per-workspace rate limiting. The annotations carry only basic hints, so this rich context adds real value.

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 longer than average, but the density is justified for a high-stakes legal review tool. It is front-loaded with the core purpose and then structured into mechanism, findings, disclaimers, and requirements. A little trimming is possible, but no sentence feels irrelevant.

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 output schema exists, the description does not need to explain return values. It covers prerequisites, failure modes, concurrency, billing, rate limits, disclaimers, and post-review retrieval. Nothing essential is missing for an agent to decide whether and how to invoke this tool.

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 schema has one required project_id with no description, so the description must compensate. It does by explaining that the project must have a saved compliance profile and be on the operator allowlist, and by referencing 'the project's saved compliance profile' and 'one review in flight per project.' This gives contextual meaning to project_id, though it never explicitly defines the parameter format or where to obtain it.

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 opens with a specific verb and resource: 'Find where a codebase creates legal exposure' and clearly scopes the job to privacy, consent, and data handling. It further distinguishes itself by explaining that findings are produced for later retrieval via get_legal_exposure_findings, separating the run action from the read action.

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 gives explicit preconditions: a saved compliance profile, a plan carrying the feature, and the project on the operator allowlist. It also gives when-not guidance by stating this is not legal advice or clearance, not exhaustive, and that an empty result is not proof of compliance. It even points the agent to get_legal_exposure_findings for reading results.

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