Create a MiniMax H3 clip (up to 15 s)

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

With no annotations, the description carries the full burden and delivers: cost of 3.3 credits per billed second charged at create time, first-15s billing cap in reference mode, 768 px short-side output, orientation inherited from the photo, and a 1-3 minute runtime with the required follow-up poll. These are exactly the operational traits an agent cannot infer from the schema.

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, but it is front-loaded with the purpose and every clause carries information (cost, limits, duration, follow-up). It is slightly packed — cost, resolution, and latency are interleaved with mode semantics — but no sentence is filler.

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 a 9-parameter generation tool with no output schema and no annotations, the description covers the full lifecycle: required inputs per mode, reference caps, billing, output format, the returned job id, and the polling step. An agent can invoke and follow through correctly without opening anything else.

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 only 56%, and the description compensates well: it specifies user_prompt is required in basic but optional in reference, that audio_clip_id drives lip-sync in reference mode, the per-type reference_files limits (8 image / 3 video / 2 audio) with reference_captions matched by order, and the 5-15s range and default of 8 for requested_duration_s. Only name, image_url, and image_path are left unexplained.

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 and resource ('Start a minimax-h3 generation from one photo') and immediately names the two operating modes, so the agent knows exactly which generation pipeline this is versus siblings like create_craftstory2_video. The scope (one photo, up to 15s) is concrete and unambiguous.

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?

Explicitly routes between mode='basic' and mode='reference' with the condition that selects each (soundtrack generated by model vs. audio_clip_id driving lip-sync), and tells the agent to call wait_for_job(model='minimax-h3') afterward. It does not, however, state when to prefer this tool over a sibling video generator, so it stops short of full alternative guidance.

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