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

Annotations cover the safety profile (idempotent, non-destructive, open-world), and the description adds genuinely non-redundant context: generation consumes the recipe's credit caps (cost implication) and does not publish (so a separate publish step follows). The idempotencyKey parameter reinforces the annotated idempotentHint. It stops short of explaining failure modes when the automation type mismatches.

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, front-loaded with the action before the constraints; no filler. The semicolon-joined final clause ('Only UGC storyboard frames; the saved automation type must match this tool') packs two distinct constraints into one crowded sentence.

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. The description does cover the key behavioral facts (no publish, credit consumption, type precondition), but for a four-parameter mutation with 0% schema coverage, the agent is left guessing about half the inputs, which is a real gap.

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 four required parameters, so the description carries the full burden and largely drops it. 'The saved recipe' loosely gestures at automationId and the type-match clause implies it must reference a UGC storyboard automation, but revision, brandId and idempotencyKey get no explanation at all – notably what 'revision' means or how idempotencyKey should be chosen.

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 (generate a sample for a saved UGC storyboard automation) and scopes it to 'Only UGC storyboard frames; the saved automation type must match this tool,' which separates it from the ~20 sibling generate_*_automation_sample tools. The phrase 'paid review sample' is domain jargon that isn't defined, but the core action 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?

Gives a precondition ('the saved automation type must match this tool') and a boundary ('Does not publish'), implying the publish/approve step is elsewhere. However it never names the alternatives an agent would actually weigh – prepare_ugc_storyboard_automation, update_ugc_storyboard_automation, or approve_automation_sample – so the when-to-use decision is only implied.

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