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

Annotations already declare mutation, destructiveness, and idempotency, so the bar is lower; the description still adds two things the annotations do not: 'App-only' (app-level auth required, not a user session) and the scope limit that it does not activate or publish. It omits whether approval is reversible, which matters given destructiveHint=true.

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?

Two short sentences with zero filler; the action and its scope are front-loaded and the exclusion trails immediately. Nothing is padded.

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 not be explained, and the annotations carry the safety profile. What still feels thin is only the parameter semantics given the 0% schema coverage; otherwise the description covers what, scope, auth, and reversibility edge cases adequately for a commit-style 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?

Schema description coverage is 0% across five required parameters. The description only loosely maps to two of them ('completed sample' -> sampleRunId, 'automation revision' -> revision) and says nothing about brandId, automationId, or the required idempotencyKey, so an agent gets no help on format or role for the majority of inputs.

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 names a specific verb+resource pair ('Approve the exact completed sample and automation revision') and scopes it to the reviewed revision, which separates it from the other approve_* siblings (approve_campaign, approve_brand_fact) and from control_automation. It could be sharper about what 'approve' commits, but an agent can distinguish it from siblings without opening the schema.

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?

It states the precondition ('the exact completed sample and automation revision reviewed in the UI') and an explicit exclusion ('does not activate or publish'), which steers the agent away from treating this as an activation call. No sibling tool is named as the alternative for activation, but the boundary is clear.

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