generate_video

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

With no annotations, the description carries the full burden. It usefully discloses that the operation is queued/asynchronous, that fields are validated by an official OpenAPI discriminator, and that the tool is off unless enabled — real behavioral context. However, it says nothing about cost implications of allow_paid/allow_unknown_cost, what identifiers are returned, or failure modes for unsupported model/parameter combinations.

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 dense sentences, front-loaded with the action and followed by the key constraint. No filler, though "the official OpenAPI discriminator validates fields" is jargon-heavy for the amount of information it delivers.

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?

This is a complex tool: a nested free-form parameters object, two paid-execution flags, a model_id that must come from list_models, and an async job whose results need get_video_generation. The description addresses none of the lifecycle or cost-safety questions, leaving an agent unable to invoke it safely on a paid model.

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 description coverage is 0%, so the description must compensate. It does explain the hardest part — that the free-form `parameters` object holds model-specific image/video/audio references validated by a discriminator — but the two cost-safety booleans (allow_paid, allow_unknown_cost) and model_id sourcing remain entirely undocumented in both schema and description.

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?

"Queue an ElevenCreative video generation" gives a specific verb (queue) and resource (video), which clearly separates it from generate_image, generate_music, and generate_sound_effect in the sibling list. It stops short of naming a related sibling such as get_video_generation, so it doesn't fully close the loop on how the queued job is tracked.

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?

"Pass model-specific text, image, video or audio references" and "Disabled by default" imply when the tool applies and hint at an availability gate, but neither is actionable: the agent is not told how to enable it, when to prefer this over other generation tools, or how allow_paid/allow_unknown_cost affect eligibility. Usage is implied rather than stated.

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