complete_review

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

With no annotations provided, the description carries the full burden, and it does substantial work: it discloses validation rules, rejection conditions, a required local-branch state, and an asynchronous approval gate keyed to task risk level. What it omits is the response shape, idempotency/retry behavior, and any authorization requirement, which matters for a write operation of this complexity.

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, purpose front-loaded, then constraints in descending order of importance, with the branch-state and approval-gating rules consolidated at the end. The semicolon-joined clauses make the last sentence dense, but no sentence is filler.

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 tool with 7 required parameters, nested arrays of evidence objects, and no annotations or output schema, the business rules are well covered but the callable surface is not. An agent still cannot tell what a successful response contains or how to construct findingClosures entries from the description alone.

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 0% across 8 parameters, so the description must compensate. It signals that findings, findingClosures, and verificationEvidence are the structured payload and implicitly ties closure status values (not_fixed, partially_fixed) to pass rejection, which adds real meaning. It says nothing about taskId, reviewRunId, summary, actorLabel, or how findingIndex maps onto the findings array, so the weighted 3 reflects partial compensation.

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: 'Record a passed or changes-requested AI review with structured findings, finding closures, and verification evidence.' That is far more informative than the bare name. It stops short of distinguishing itself from siblings like approve_review or request_changes, which occupy adjacent decision-recording territory.

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 states the conditions under which a 'passed' decision is rejected (unmet or unverifiable acceptance criteria, prior not_fixed/partially_fixed findings) and the risk-based gating (low-risk auto-completes after the branch check, medium/high wait for developer approval). That is genuine usage context. However, it never says when to call this versus approve_review, request_changes, or start_review, leaving sibling routing to inference.

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