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

Annotations only declare the generic mutation/safety profile; the description adds the traits that actually matter: 3 credits per set charged from the account, a few minutes to render, automatic refund on failure, and server-side rotation when format/style are omitted. That async-plus-cost-plus-refund picture is exactly the behavioral context annotations cannot express.

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?

Four tight sentences, front-loaded with what gets produced and for whom, then cost/latency, then parameter behavior, then the required next step. No filler and no repetition of enum values already in the schema.

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?

No output schema exists, and the description covers queuing, cost, timing, failure refund, and how to retrieve results via list_carousels. The one gap is what the call itself hands back (a job or carousel id) needed to correlate the later poll.

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 coverage is 100%, so baseline is 3, and the description earns above it by explaining what 'format' actually controls (the content idea, with examples) versus 'style' (the visual look), plus the non-obvious semantics of omitting either — rotation into a combo not recently tried. product_id is left to the schema.

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 and resource — 'Queue a multi-slide carousel (Instagram and TikTok slides) for one catalog product' — and immediately scopes it to real product facts. It is clearly distinct from list_carousels, which is named as the polling companion, and from the other generate_* siblings by naming the output medium.

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 clear operating context: one catalog product per call, optional format/style with rotation on omission, and an explicit follow-up step ('Poll list_carousels for download links'). It does not, however, say when to choose this over adjacent generators like generate_static_ads or generate_clips, so the alternative-selection guidance is incomplete.

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