Start Review Round

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

Annotations indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the description adds value by specifying background execution, immediate return of a polling ID, and automatic persistence of AI evidence. It clarifies that no manual operator attachment is needed, which is useful beyond the annotations. However, it does not disclose potential side effects like external API calls or resource consumption.

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 concise, consisting of two clear sentences that front-load key information (background execution, polling, evidence handling). However, it could be slightly more structured by outlining the return value or prerequisites without becoming verbose.

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?

Given the tool has 10 parameters, 30% schema coverage, no output schema, and many sibling tools, the description is insufficient. It does not explain the return value structure (beyond session_id/job_id), prerequisites like an existing session, or the difference from related tools like session_start_unanimous. Essential context is missing for an agent to use the tool correctly without additional information.

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?

With schema description coverage at only 30%, the description must compensate but only mentions the 'evidence' parameter and its auto-persistence. Other parameters like task, draft, peers, caller, review_focus, etc., are not explained in the description. The schema does have some descriptions (e.g., for evidence, review_focus, reasoning_effort_overrides), but the lack of description coverage leaves many parameters undocumented, making the tool harder to use correctly.

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 the tool starts a real peer-review round in the background and returns a session_id/job_id for polling. It uses a specific verb ('Start') and resource ('real peer-review round'), distinguishing it from other session tools by mentioning background execution and auto-persistence of evidence. However, it does not explicitly contrast with siblings like session_start_unanimous.

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 implies the tool is used when an AI needs to initiate a peer review with automatic evidence submission and polling. However, it provides no explicit guidance on when to use this tool over alternatives (e.g., session_start_unanimous, ask_peers) or when not to use it. Missing exclusions or prerequisites.

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