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

Annotations cover the safety profile (destructive=true, idempotent=true, readOnly=false), and the description adds genuine context beyond them: it discloses that the reviewed sample is invalidated (an irreversible side effect) and explicitly clarifies what the tool does NOT do (generate/publish). This is meaningful added value on top of the 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 compact sentences, front-loaded with the core action, followed by the non-actions and the type constraint. No filler, though 'Only written carousel sections' is terse to the point of ambiguity.

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 needn't be described. But given 0% schema coverage, nested objects, and 5 required params (including concurrency/idempotency fields like revision and idempotencyKey), the description does not supply enough to safely call the tool without reading the schema.

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 parameters including a large nested recipe object. The description only gestures at 'recipe' and mentions the automation type; it says nothing about brandId, automationId, revision, or idempotencyKey, leaving the agent with no field-level guidance where the schema provides none.

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+object: replacing the automation's recipe (and invalidating its reviewed sample). This clearly distinguishes it from the sibling prepare_*, activate_*, and generate_*_sample tools for the same carousel automation. It lacks an explicit sibling reference, but the operation is unambiguous.

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 description implies scope by stating 'Does not generate or publish' and 'the saved automation type must match this tool,' which steers the agent away from generation/publishing flows. However, it never names the alternative tool (e.g., generate_carousel_creator_automation_sample) or states prerequisites like when a reviewed sample exists to invalidate. Usage is implied rather than explicit.

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