Create a CraftStory 2.0 talking video (photo + audio)

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

No annotations exist, so the description carries the full burden, and it delivers: credits are charged on create (with a pointer to preview_cost), refunded on failure, the job returns an id and initial status, and generation takes 8-15 minutes requiring repeated polling. This is exactly the operational context an agent needs before committing.

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?

A single dense paragraph that is front-loaded with what the tool produces, then input formats, then cost and lifecycle. Every clause is substantive, though the run-on structure packs many distinct facts into one block rather than separating them.

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 11-parameter async generation tool with no output schema and no annotations, the description covers the return values (job id + initial status), the async polling pattern, cost/refund behavior, and input alternatives. Nothing essential to correct invocation is missing.

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 already 91%, so the baseline is 3. The description adds useful semantics on top: resolution is WIDTH_HEIGHT with portrait vs landscape values, audio can be any length and plays in order, and the photo may come from image_url, image_path, or a scene_id custom avatar. The format hint for resolution goes beyond the bare enum.

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?

Starts with a specific verb and resource ("Start a craftstory-2 generation") and immediately describes the input modes: a person's photo, a custom avatar scene via scene_id, speaking audio clips with lip-sync and gestures. The named model (craftstory-2) implicitly separates it from the sibling create_minimax_h3_video, so an agent can pick correctly.

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?

Describes the full invocation workflow: start the job, poll with wait_for_job(model='craftstory-2') until done, then get_job_result, and use upscale_video for 1080p afterwards. It does not give an explicit exclusion rule against create_minimax_h3_video, but the model naming and the described pipeline give clear context.

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