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

Annotations indicate non-read-only and non-destructive behavior. The description adds valuable behavioral context: 'Publishes a finding.review event' and 'open a debate window' for challenges. It discloses side effects and constraints beyond what annotations provide, without contradicting them.

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 three sentences, front-loads the core action and options, and includes constraints and side effects without any wasted words. It is highly efficient and well-structured.

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 3 parameters (2 required) and no output schema, the description covers purpose, constraints, and side effects. It omits details about the debate window's behavior or response format, but those are not critical for invocation. The description is sufficiently complete for an agent 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 67% (finding_id and rationale have descriptions, kind does not). The description clarifies the meaning of the kind enum by explaining 'verify' as real and 'challenge' as opening a debate window, which adds semantic value beyond the schema's bare enum. The other parameters already have adequate schema descriptions, so the description compensates well for the missing kind description.

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 states a specific verb ('peer review') and a specific resource ('finding'), and enumerates the two possible actions (verify or challenge). It distinguishes itself from sibling tools like review_output by focusing on findings rather than outputs, and adds a clear constraint ('You cannot review your own finding'). The purpose is unambiguous and differentiated.

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 usage constraints: 'You cannot review your own finding' and 'each kind can be filed once per finding.' It implies the tool is for reviewing findings, not outputs, which separates it from review_output. However, it does not explicitly name alternatives or state when not to use this tool beyond the self-review restriction, so a small gap remains.

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