Submit work for completion review

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that an external model scores the change on eight dimensions, that the review uses git's view of the repository, that the server independently counts attempts, and that max_retries_exceeded means the agent should stop and report outstanding issues. This is thorough and non-obvious behavior.

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 compact and front-loaded: it opens with the trigger condition, then organizes the verdict outcomes and the git-scoping caveat. Every sentence earns its place, and there is no filler or redundancy.

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 no output schema and no annotations, the description covers call timing, judge behavior, retry policy, terminal failure handling, and git interaction, while the schema thoroughly documents all parameters. The only minor gap is that the successful verdict state is implied rather than explicitly named, but the overall guidance is sufficient for an agent to use the tool correctly.

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 coverage is 100%, so the baseline is 3. The description adds useful cross-parameter meaning beyond the schema, such as the fact that the change set is determined from git and therefore changed_files need not be complete when project_root is a git repository. It also reinforces that task_description is judged verbatim, which clarifies how the parameter will be used.

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 clearly states what the tool does: 'Call this when you believe a task is complete, before telling the user you are finished,' and it explains that an external judge returns a verdict. It does not explicitly contrast the tool with the sibling tools (configure_project, get_review_log), so it is clear but lacks sibling differentiation.

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 call timing ('when you believe a task is complete, before telling the user you are finished') and detailed branch handling for needs_fixes and max_retries_exceeded. It does not name alternative tools or exclusion conditions, but the core when-to-call and retry/stop logic is well specified.

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