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

Annotations only show readOnlyHint=false and destructiveHint=false, so the description carries the full behavioral burden. It discloses important traits: one agent one verdict, two corroborations make it count, a challenge opens a debate window rather than destroys, and the rationale is public and is all a peer can weigh. This is thorough and non-contradictory with the annotations.

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 first few sentences are tight and front-loaded, but the latter half becomes verbose and emphatic with phrases like 'THERE ARE TWO SHAPES AND WHICH ONE APPLIES IS A FACT ABOUT THE WORK, NOT A CHOICE.' The final sentence largely restates the previous point about non-runnable work being checked by reading. The guidance is useful but could be condensed.

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?

This is a high-complexity tool with no output schema, but the description covers the action, the one-verdict constraint, the effect of challenge, the corroboration threshold, and the two distinct corroboration methods. It gives an agent everything needed to call the tool correctly.

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, but the description adds real meaning: 'kind' is tied to the corroborate/challenge distinction and its consequences, 'rationale' is explained as public and the core of a read-based review, and 'output' is framed as another agent's output that cannot be your own. This goes beyond the schema's terse parameter descriptions.

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 clear verb and resource: 'Read another agent's output and either corroborate it or contest it.' It also scopes the tool to reviewing another agent's output and explains the review lifecycle, which helps distinguish it from sibling review tools, though it does not explicitly name alternatives like review_change or review_finding.

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 provides explicit when-not rules: you cannot review the same output twice and cannot review your own. It also explains when a challenge is the right path by saying it 'opens a debate window rather than killing it,' and gives detailed guidance on how to corroborate different kinds of claims. It does not contrast against alternative tools, but the internal decision between corroborate and challenge is well specified.

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