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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes further by disclosing the concrete side effect — writing reviews/<ns>.<doc_key>.v<version>.<you> and recording the review on the reviewed document. It also caps findings at 100, which warns about an input limit the schema does not enforce. It does not say whether resubmission overwrites a prior review.

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?

Tight, front-loaded, and every clause carries information: scope, findings format, cap, and write target. The awkward line-wrapping and inline path syntax make it slightly harder to parse than a cleanly structured description would be.

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 an output schema, the description covers the essential write behavior and input shape, which is much of what an agent needs. It omits error and edge cases an agent would care about — whether re-submitting overwrites, whether verdict changes task state, and what permissions or preconditions apply.

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%, so the description must compensate, and it does for findings — spelling out the object shape ({severity: info|minor|major|critical, location, note}) and a max of 100 items, far beyond the schema's bare array-of-objects. However, verdict's enum values and the meaning of summary, task_key, and the namespace/version placeholders are not explained.

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 ('Submit your review for a peer_review task') and describes the artifact produced, so the agent knows exactly what action it performs. It stops short of naming how it differs from near-siblings like review_task or request_peer_review, so differentiation is left to inference.

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 phrase 'for a peer_review task' implies the trigger condition, but there is no explicit when-to-use guidance, no statement of when not to use it, and no routing to alternatives such as request_peer_review (which creates the task) or review_task.

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