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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses real side effects: accept publishes the escrow.release outbox event and creates worker_payouts; reject creates a disputes row; request_changes reopens the task, archives superseded proof, extends the deadline, and keeps escrow held. It also surfaces the `change_request_limit_reached` error. No annotation contradiction exists.

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 dense but not bloated: it front-loads the core purpose, then organizes each branch by decision type, and ends with the limit/error behavior. Every sentence carries operational information useful for correct invocation, with no filler or redundant restatement of the schema.

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 mutation tool with no output schema, the description covers the essential operational context: side effects of each decision, when each branch should be selected, the retry limit, the deadline extension, and the error response. An agent has enough information to invoke the tool correctly and anticipate outcomes.

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 meaningful behavior beyond the schema by explaining what each `decision` value actually triggers (payouts, dispute, resubmission) and why `reason` is necessary ('read by a person'). It does not add much for `task_id`, but the extra `decision` semantics justify a 4.

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 action and resource: 'Review submitted proof' and immediately enumerates the three possible decisions (`accept`, `reject`, `request_changes`). This clearly differentiates the tool from review-adjacent siblings like `submit_rating` and `submit_experience_feedback`, and matches the annotation title 'Review completion proof'.

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 when-to-use guidance: request_changes is for 'incomplete or ambiguous' proof 'rather than wrong', and is called 'the right call far more often than rejecting'. It also provides a hard when-not boundary: a task may be sent back at most twice before accept/reject is mandatory, with the resulting 409 error. This is concrete decision-rule guidance.

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