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

Annotations already declare the write/open-world/non-idempotent profile, and the description adds the cost model (2 credits, premium more) and the asynchronous polling workflow, which are genuinely useful beyond the structured fields. It stops short of saying what identifier is returned or failure behavior.

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?

Two compact sentences, front-loaded with the capability statement followed by cost and polling guidance. Enumeration of camera moves is slightly redundant with the schema but not wasteful.

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?

Covers duration, input limits, cost, model selection pointer and how to retrieve results — enough for a 7-parameter creation tool with no output schema. Minor gaps remain around error cases and whether the reference image becomes a start frame in practice.

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?

With 71% schema coverage, the schema already documents model, aspect, prompt and reference_images. The description restates the camera enum values and the 3-photo cap without adding syntax or interaction rules, so it adds marginal value over 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+resource ('A short video (4-10 s) from your own prompt') plus its distinctive capabilities: reference photos, camera moves, sound. It clearly separates itself from create_image, generate_clips and make_cinematic by scoping duration and inputs.

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 actionable routing: check get_create_options for premium models and poll list_creations for results. It does not explicitly say when to prefer this over create_image or generate_clips, so the sibling differentiation is implied rather than spelled out.

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