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

Annotations cover the non-read-only, non-idempotent nature. The description adds credit costs (12 for 15 s, 18 for 30 s), notes that premium models cost more, and signals async behavior by saying to poll list_creations. It does not mention failure modes or generation time.

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?

It is dense and front-loaded, and nearly every clause carries information (purpose, inputs, cost, polling). The opening sentence is slightly awkward and redundant ('banner... ads and banners').

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?

For an async, credit-consuming generation tool with no output schema, it covers cost, input alternatives and how to retrieve results. It omits what the immediate response contains, such as a creation id.

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 60%. The description explains the product_id-or-images input choice and ties seconds to cost, and it hints that model options come from get_create_options. Mood and language are left undocumented beyond their enums.

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?

It states clearly that the tool produces a 15 or 30 s image film of a product with a pro model, with frames usable as banners. It does not say how this differs from siblings like create_video or generate_clips, though the brand-film/banner framing hints at the distinction.

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?

Use cases are given (site, ads, banners), and it points to get_create_options for premium models and list_creations for polling. There is no when-not-to-use guidance and no contrast with create_video or generate_clips.

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