review_advisory

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

With no annotations, the description carries the full burden and does meaningful work: records are persisted in Git, relevant changes reopen reviews, and recorded identities are assertions rather than authenticated approvals. That last point is an important security caveat an agent could not infer from the schema. It omits error behavior, idempotency, and any permission requirements, so it is not exhaustive.

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?

Four sentences, front-loaded with the core operation before the routing and lifecycle caveats. Every clause carries signal (sibling routing, reopen semantics, auth caveat), though the first sentence is overpacked and would read better split.

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 7-parameter, no-annotation, no-output-schema tool, the description explains the concept and some lifecycle behavior but leaves required-parameter semantics (findingId, baselinePath) and the prepare-vs-record workflow unclear. Given the low schema coverage, it should carry more of that load.

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 only 14% (just 'dir'), so the schema does not do the heavy lifting. The description names reviewToken, reviewer, note, and the three outcome actions, which maps to the action enum and three optional params, but the three required params (dir, baselinePath, findingId) are never explained and no format or validation details are added.

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 names a specific verb pair (prepare/record) and a specific resource (a repair advisory review, with addressed/inapplicable/deferred outcomes), and it explicitly differentiates from the sibling review_decision. The prose is dense and the underlying artifact ('original repair advisory', reviewToken lifecycle) is only loosely defined, which keeps it short of a 5.

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 routes decision findings to review_decision and states this tool never approves decisions, giving a clear when-not condition and naming the alternative. It also notes that relevant changes reopen reviews while unrelated commits preserve them. It does not say when to use the prepare action versus recording an outcome, so it stops short of fully explicit guidance.

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