Start Review Round

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

Annotations already indicate the tool is not read-only, not idempotent, and not destructive. The description adds that the round runs in the background and returns immediately for polling, which is key behavioral context. However, it does not disclose potential side effects like resource usage or state changes beyond the returned ID.

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 a single sentence, which makes it concise and front-loaded. However, it omits essential information about parameters and usage, so it is under-specified rather than efficiently complete.

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 9 parameters (2 required), nested objects, many siblings, and no output schema, the description is too minimal. It explains neither the output format beyond a session ID nor how to use the various parameters, leaving the agent with insufficient information to use the tool effectively.

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?

Only 22% of parameters have descriptions in the schema (review_focus and reasoning_effort_overrides). The tool description itself provides no parameter explanations. Required parameters task and draft, along with session_id and others, remain opaque. The description fails to compensate for the low schema coverage.

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 it starts a real peer-review round asynchronously and returns an identifier for polling. The verb 'start' and resource 'peer-review round' are specific. However, it does not differentiate from sibling tools like session_start_unanimous or ask_peers, which also start review processes.

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?

No guidance is provided on when to use this tool versus alternatives such as session_start_unanimous or ask_peers. Given the large number of sibling tools, this omission forces the agent to infer usage from context, which is unreliable.

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