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

Annotations already flag destructiveHint and idempotentHint, so the bar is lower, and the description still adds non-obvious substance: the reviewed sample is invalidated and the saved automation type must match. It leaves out what happens on a revision conflict or why idempotencyKey is required.

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, zero padding, with the core mutation and its main side effect front-loaded before the scope constraint. Every sentence 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?

An output schema exists, so return values need no explanation, and the behavioral scope is well covered. The gap is parameter guidance: with 0% schema coverage and a deeply nested recipe object, an agent still lacks enough to construct a valid call confidently.

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, including a large nested recipe object, so the description carries the burden and fails to compensate. It implies the recipe is replaced wholesale but says nothing about revision, idempotencyKey, brandId, or automationId semantics.

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 concrete verb and resource ('Replace this automation's recipe') plus a side effect ('invalidate its reviewed sample'), so the action is unambiguous. It also scopes itself ('Only advertising artwork') against the wider update_* automation family, though it never names a specific sibling.

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 supplies clear negative guidance — 'Does not generate or publish' — which steers the agent away from the generate_* and activate_* siblings. However it gives no prerequisites (revision matching, idempotency behavior) or explicit when-to-use versus prepare_/update_ alternatives.

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