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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds meaningful consequence detail: replacing the recipe 'invalidate[s] its reviewed sample', which tells the agent downstream side effects beyond the annotation. It also scopes the write ('Does not generate or publish') and states the type-matching constraint, adding context the annotations alone do not convey.

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, each front-loaded and carrying distinct information: what it does, what it does not do, and the type constraint. No filler or restatement of the name/title.

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 mutation semantics are reasonably covered. However, for a tool with a deeply nested recipe object and 0% schema description coverage on all five required params, the description leaves revision and idempotency semantics unaddressed, so it is only minimally sufficient for the complexity involved.

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% and there are 5 required parameters, including nested objects. The description only gestures at 'recipe' and never explains revision (optimistic concurrency), idempotencyKey, automationId, or brandId, so an agent gets little semantic help beyond the schema. With zero coverage the description should compensate more than it does.

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 ('Replace this automation's recipe and invalidate its reviewed sample') and immediately differentiates from the family's other operations by declaring 'Does not generate or publish', positioning it against generate_*_sample and activate_* siblings. The closing clause 'Only UGC storyboard frames; the saved automation type must match this tool' pins the exact tool within the update_* family.

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?

Clear usage context is given via exclusion ('Does not generate or publish') and a precondition ('the saved automation type must match this tool'), which tells the agent when this tool applies versus sample-generation or activation tools. It stops short of explicitly naming the alternative tool to use for generating the sample, so it is strong but not fully directive.

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