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

Goes well beyond the annotations by disclosing downstream side effects: a safety reason halts this contact in the campaign and flips an Autopilot campaign to Copilot. It also warns that the operation is bound to the read revision and that a conflict requires re-reading before retry, which is exactly the recovery guidance a destructive, non-idempotent mutation needs.

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?

Four tight sentences, front-loaded with the action, then the regenerate toggle, then the safety-reason exception, then the revision/conflict rule. No sentence is filler and each adds a distinct operational fact.

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 destructive nested-body mutation with no output schema, it covers side effects, conditional outcomes, and retry-after-conflict behavior. The remaining gap is that it doesn't say what comes back on success or which errors other than revision conflict can occur.

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 0%, so the description carries the burden, and it explains the two least self-evident fields: regenerate changes whether a replacement draft is produced, and expected_revision ties the call to a specific read with conflict semantics. It also clarifies that the reason field has a behavioral branch (safety reasons vs. stylistic ones), though 'note' and 'messageId' remain 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?

States a specific verb and resource ('Rejects one draft in Review with a reason') and pins the scope to a single draft, which implicitly separates it from the bulk sibling. It does not explicitly name an alternative tool, so the differentiation is inferred rather than stated.

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 conditional guidance: use regenerate when you want a replacement written against the reason, omit it when the reason is informational, and use a safety reason to stop the contact and downgrade the campaign. It never states when to prefer bulkDenyMessages, skipMessage, or returnQueuedMessageToReview over this tool, so the routing against siblings is left to the agent.

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