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

Adds substantial context beyond the annotations: it may incur paid AI cost, it is not an approval/send action despite destructiveHint=true, it needs outreach:write scope, and concurrent edits survive via the revision check. It stops short of saying what happens to the existing draft body when regenerated, which is the main destructive behavior the annotation implies.

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?

Three compact sentences front-loaded with the action, then cost/safety, then parameter guidance. Only redundancy is the repeated title line, which adds nothing.

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?

An output schema exists so return values need no explanation; the description covers the remaining gaps an agent needs — cost, permissions, safety boundary, and concurrency semantics — for a two-parameter mutation tool.

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 0% schema coverage for the description field, the definition carries the load and does explain the critical 'revision' parameter as an optimistic-concurrency token ('Supply the current revision; concurrent edits are preserved'). The draftId parameter's meaning is only covered by the schema's inline description, not this text.

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?

States a specific verb (regenerate) and resource (one pending comment draft) plus the mechanism (existing comment writer, current workspace-observed post context). It implicitly separates itself from decideCommentDraft by noting it 'never approves or sends', though it never names a sibling explicitly.

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?

Gives clear context for when this is appropriate (a draft is pending and needs a fresh generation) and a negative boundary ('never approves or sends'), which steers the agent away from the decide tool. It also flags a prerequisite ('Requires outreach:write') and a cost signal ('May invoke paid AI'), but names no alternative sibling for the edit-vs-regenerate choice.

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