submit_review_decision

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

Annotations only declare the generic profile (not read-only, not destructive, not idempotent); the description goes well beyond that by spelling out the state machine: approved moves the task to done and records commit_hash on the latest attempt, changes_requested below the retry cap returns it to pending for anyone to claim, and at cap it goes to needs_human_review. What is missing is reviewer authorization requirements and whether a submitted decision can be revised afterwards.

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?

Front-loaded with the core purpose, then the two branch outcomes in a compact enum-style summary; every sentence carries real state-transition information. The 'decision ∈ {approved, changes_requested}' notation is terse but appropriate, and there is no 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 non-idempotent mutation with no output schema, the description covers the essential consequences of each call, which is what an agent most needs before invoking it. It falls short only on the undocumented Comments/as_agent parameters and the absence of any note on permissions or result reporting.

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% and none of the five fields carry enums, so the description must compensate: it supplies the Decision enum (approved, changes_requested) and explains that CommitHash is optional and gets recorded on the latest attempt. TaskId is self-evident, but Comments and as_agent are never explained, leaving two of five parameters undocumented in both schema and description.

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?

States a specific verb and resource: a reviewer's verdict on a task that is in review, with the two allowed decision values. An agent can tell this is a review-submission action, though the description never names the closely related siblings (submit_verification_verdict, submit_attempt_verdict, override_verdict) to disambiguate which verdict tool applies where.

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?

Usage is implied by 'a reviewer's verdict on a task in review' plus the decision enum, so the context of use is inferable. But there is no explicit when-not-to-use guidance and no routing to alternatives such as override_verdict or the other submit_*_verdict tools, leaving the agent to guess which submission tool fits a given review situation.

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