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

Annotations already declare idempotentHint=true, destructiveHint=true, and readOnlyHint=false; the description adds genuinely useful context beyond them ('App-only' auth posture and the scope limit 'does not activate or publish'). It does not explain why the operation carries destructiveHint=true (e.g., whether approving one revision invalidates others) or what state changes result, leaving the destructive profile opaque.

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, front-loaded sentences with no filler; the scope clarifier follows immediately after the purpose. However, for a five-parameter destructive mutation the brevity edges into under-specification rather than tight conciseness.

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, and annotations cover the safety profile. But with no parameter descriptions and a destructive, idempotent write, the description omits prerequisites (must match the reviewed revision), idempotency behavior, and the consequence of approval, leaving real gaps for an agent to act on.

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, so the description carries the full burden. It only implicitly touches automationId/revision ('automation revision') and sampleRunId ('sample'), leaving brandId, the revision-vs-sampleRunId relationship, and idempotencyKey semantics entirely unexplained, including the practical need to match the revision the sample was generated against.

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 (approve) and resource (completed sample and automation revision), with the qualifier 'exact ... reviewed in the UI' pinning down which sample. It also distinguishes itself from the activate_* sibling family by stating 'does not activate or publish'. It stops short of naming which sibling produces the sample or what activation follows, but the purpose is clear.

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 'reviewed in the UI' implies the prerequisite workflow (generate/prepare a sample, inspect it, then approve), and 'App-only' signals who may call it. However, against a sibling list containing generate_*_automation_sample, prepare_*_automation, and activate_*_automation, it never explicitly states the when-to-use condition or the downstream alternative, so routing relies on inference.

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