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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond them: the recipe is replaced wholesale (not merged) and the reviewed sample is invalidated, a destructive side effect an agent would otherwise not anticipate. It does not mention authorization requirements or what a revision conflict does.

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 short sentences with the primary action front-loaded and no filler. The trailing 'Only banner artwork; the saved automation type must match this tool' is telegraphic and slightly ambiguous, which is a clarity nit rather than bloat.

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?

The output schema exists and annotations cover the safety profile, so those areas need no prose. However, for a complex mutation with a large nested recipe and mandatory revision/idempotencyKey, the description omits the concurrency semantics of 'revision' and the purpose of the idempotency key; it is adequate but leaves meaningful gaps for a tool of this complexity.

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?

Five required parameters with 0% schema description coverage, including a deeply nested 'recipe' object with roughly twenty fields whose meaning is nowhere explained. The description mentions 'recipe' only obliquely and never clarifies revision (optimistic concurrency), idempotencyKey, or any recipe field, so it fails to compensate for the total absence of parameter documentation.

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 (Replace) on a specific resource (this automation's recipe) plus the notable side effect that the reviewed sample is invalidated. It also routes away from siblings by declaring 'Does not generate or publish' and scoping to 'banner artwork', so an agent can distinguish it from generate_banner_generator_automation_sample and activate_banner_generator_automation without opening a 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?

'Does not generate or publish' is an explicit when-not that steers the agent toward the generate/enable siblings for those outcomes. It stops short of naming those alternatives outright or describing prerequisites (e.g. needing an existing automation vs the prepare_* path), so it is clear context but not a full routing guide.

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