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

Annotations already declare idempotentHint=true, destructiveHint=true, and openWorldHint=true, but the description adds real context beyond them: it requires user authorization to post, clarifies the visibility=all semantics ('exposes prose to clients; raw evidence remains private'), and warns that normal comment notifications and integrations may fire. The idempotency sentence largely restates the annotation, which keeps this at 4 rather than 5.

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?

Five short, front-loaded sentences with the primary action stated first. Most sentences carry distinct information (authorization, idempotency, visibility, notifications), though the idempotency sentence is partially redundant with the annotation.

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?

With an output schema present, return values need not be described, and annotations plus the description cover the mutation safety profile. The main remaining gap is that the description never explains the batch nature (up to 15 findings) or the expectedRevision concurrency contract, both of which an agent must handle 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%, so the schema documents the core fields. The description adds meaning for the visibility enum ('all exposes prose to clients') that the schema does not, but says nothing about expectedRevision, findingId, or the 15-item batch cap, leaving part of the parameter surface unexplained.

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 and transformation: 'Publish explicitly selected suggestions as ordinary comments.' An agent can tell this converts review findings into comments rather than creating them from scratch. It stops short of naming the sibling it differs from (e.g., create_comment or update_review_finding), so differentiation is implicit rather than explicit.

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 'explicitly selected suggestions' and the authorization requirement imply usage comes after a review run with user-approved findings, but there is no explicit when-to-use, when-not, or named alternative. The selection/authorization prerequisite is the only routing signal.

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