Video from a prompt

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose real traits beyond the schema: output is always an mp4 file in the output directory and never inline, and long jobs return a generation_id rather than the video. However, it omits permissions/auth requirements, moderation behavior beyond the single 'stricter moderation' aside, and any failure/retry semantics for a long-running paid job.

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?

Three dense sentences that front-load what the tool does, then output format, then pricing. Every clause carries information, though the parenthetical model list and the multi-clause duration sentence push it toward density over readability.

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, no-annotation, no-output-schema tool, the description covers the important unknowns: where output lands, how async jobs resolve, and how duration affects cost. It leaves a few gaps (the private feed default, negative_prompt behavior) that the schema partially covers, but nothing critical to calling it correctly 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 description coverage is already 100%, so the baseline is 3, but the description adds genuine meaning the schema does not: omitted duration causes Seedance to be quoted at its maximum length, generate_audio roughly doubles the price and the dry-run quote excludes it, and resolution tiers on MiniMax are upscaled. That pricing/default interaction is the kind of context the schema can't carry.

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 concrete verb+resource combination: generate a video from a text prompt, and names the four supported models up front. 'From a text prompt' implicitly separates it from the sibling video tools (ideogram_video_image, ideogram_video_reference), but those siblings are never named, so the distinction rests on inference rather than explicit contrast.

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?

Routes the agent to two alternatives with conditions: use ideogram_quote to price a call first, and use ideogram_generation to resume a job when a generation_id is returned. Also specifies when to supply duration (to get an accurate price). It stops short of saying when to prefer this tool over the other video-generation siblings.

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