Create a MiniMax H3 clip (up to 15 s)

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

Goes well beyond the annotations (non-readOnly, openWorld, non-idempotent, non-destructive) by disclosing cost (3.3 credits per billed second, charged on create, first 15 s billed for audio), async job semantics, output resolution and orientation behavior. That billing-on-create detail is exactly the kind of behavioral trait 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 mode split, then progressively adds conditional detail; nearly every clause carries operational information. It is a dense single block rather than cleanly structured, but there is little filler to cut.

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?

With no output schema, the description supplies the return contract itself (job id) and the polling path to completion, plus cost, duration expectations, and output geometry. For a 9-parameter async generation tool, an agent has everything needed to call it and interpret the result.

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 for the undocumented parameters: it explains the mode-dependent meaning of user_prompt and audio_clip_id, the 5-15 s range and default 8 for requested_duration_s, and the caps on reference_files (8 image / 3 video / 2 audio) plus reference_captions ordering. It leaves name, image_url and image_path entirely unexplained, and 'mode=reference: the reference model' is a vague gloss rather than a real definition, so it stops short of full coverage.

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+resource ('Start a minimax-h3 generation from one photo') and enumerates the two operating modes, which is enough to separate it from siblings like create_craftstory2_video and upscale_video. The scope constraint (up to 15 s, 768 px short side) further pins down what is being created.

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 branches on mode ('basic' vs 'reference') and on the presence of audio_clip_id, telling the agent exactly which parameter set to supply in each case. It also names the required follow-up call (wait_for_job with model='minimax-h3') and its expected 1-3 min runtime, so the agent knows the full workflow, not just the trigger.

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