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

Annotations cover the safety profile (destructiveHint=true, idempotentHint=true), but the description adds non-obvious traits they don't: the change 'does not activate' the automation, and auto mode carries prerequisite consent. It doesn't clarify whether the existing delivery setting is overwritten, but the added context is substantial. No contradiction with annotations.

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 tight sentences, front-loaded with the action, then preconditions, then the 'App-only' constraint. Zero waste; every clause earns its place.

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 covering return values and annotations covering safety, the description is nearly complete: it conveys purpose, preconditions, and the non-activating behavior. The remaining gap is parameter-level detail (revision, idempotencyKey), which neither schema nor description supplies.

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 5 required params. The description only adds meaning to the delivery enum ('review' vs 'auto') and implicitly automationId; it says nothing about brandId, revision, or idempotencyKey semantics, leaving most parameters undocumented in both schema and prose.

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+resource ('Set ... delivery') and scopes it to two modes (review or auto) for automation. However, it never distinguishes itself from close siblings like update_automation or control_automation, so the agent must infer which is the right setting tool.

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 a clear precondition ('after explicit user confirmation') and states the requirements for the auto path ('requires a reviewed sample and publishing consent'), which is genuinely useful routing context. It stops short of naming alternatives or negative cases (e.g., when to prefer update_automation).

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