review_task

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

With no annotations, the description carries the full burden, and it does disclose two real behavioral traits: the reviewer is restricted to Read/Grep/Glob (read-only, cannot mutate) and it will never repair issues found. That is meaningful. It omits other behavioral facts an agent needs, such as the trust/permission model, timeout behavior, and what the review returns.

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 single semicolon-delimited clause is front-loaded and waste-free, but it is under-specified rather than concise for a tool with 8 parameters and no annotations. The brevity is efficient but leaves core meaning unstated.

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?

An output schema exists so return values need not be explained, but for an 8-parameter, 4-required task-review tool with zero annotations and 0% schema coverage, the description is far too thin. Required inputs beyond 'acceptance', the meaning of 'fresh' context, and the relationship to sibling task tools are all missing.

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 (4 required), so the description must compensate and largely does not. It covers only 'acceptance' ('acceptance is required'); job_id, original_task, cwd, model, timeout_sec, project_root, and execution_summary get no explanation of format or role. Only project_root carries an inline schema 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 verb (review) and a constraint set (Read/Grep/Glob-only, fresh context, never repairs), which hints at a read-only code review task. However, 'CC' is unexplained jargon and the description never names the resource being reviewed (a job/task) or distinguishes itself from siblings like execute_task or run_job beyond the word 'review'. An agent must infer quite a bit.

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 sentence 'acceptance is required; never repairs' states a precondition and a hard limitation but gives no when-to-use guidance relative to siblings (execute_task, continue_task, run_job). Nothing tells the agent when to choose review_task over running or continuing a task.

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