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

Annotations are minimal, so the description carries the burden and does so: it discloses the async contract (returns {job_id}), the required polling loop via job_status, where the result lands (result.video), and a durability caveat ('Jobs are in-memory: poll promptly — a redeploy can drop an in-flight job (job_not_found) → resubmit'). That is the kind of operational 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?

Front-loaded with the core action and the async contract, then prerequisites and caveats in descending priority. Slightly padded by the model-name roster ('Seedance, Kling, Veo, WAN, Flux, Nano Banana, etc.'), which is illustrative but not load-bearing.

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, so the description supplies the return shape itself ({job_id}, then result.video). Combined with the polling protocol, the job-loss caveat, and the routing guidance to siblings, an agent has everything needed to invoke this correctly end-to-end.

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 67% schema coverage and a nested params object, the description adds real meaning beyond the schema: it enumerates the accepted param keys, explains that image edit/reference models accept image_url OR image_urls OR reference_urls interchangeably, and that image_url switches video generation into image-to-video. It also anchors model_id to list_models.

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 ('Generate') and resource ('media') scoped to the full Media Forge model catalog, and explicitly carves out the video_editor_* sibling tools for reference/dialogue work. An agent can distinguish this from every sibling without opening a schema.

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 an explicit prerequisite ('Call list_models FIRST and pass an exact id from it'), a conditional rule ('use i2v_id when you supply image_url, t2v_id otherwise'), an error consequence ('Unknown ids error at submit'), and an alternative ('For reference + spoken dialogue, prefer the video_editor_* tools'). Nothing is left to inference.

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