Create a MiniMax H3 clip (up to 15 s)

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

Annotations cover the safety profile (not read-only, open-world, non-idempotent, non-destructive). The description adds valuable context beyond that: cost (3.3 credits/billed second, charged on create), output resolution (768 px short side), orientation behavior, and the async flow with wait_for_job. It could disclose more about failure/retry but is unusually transparent for a create tool.

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 purpose, then mode-specific guidance, then cost/output/async details in a compact flow. It's dense but every clause earns its place; only slightly overloaded with parenthetical constraints.

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?

Given 9 params, 56% schema coverage, no output schema, and an async job flow, the description supplies the missing operational details (cost, output size, job id + wait_for_job poll). It is essentially complete for correct invocation, though the image input fields are lightly documented.

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 56%, so the description must carry weight, and it does: it explains that user_prompt is the scene description and required in basic mode, that audio_clip_id drives the clip in reference mode, the limits on reference_files (up to 8 image / 3 video / 2 audio), and reference_captions ordering. Minor gaps remain for name/image_url/image_path/requested_duration defaults.

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?

Specific verb+resource ('Start a minimax-h3 generation from one photo') plus a clear distinction between the two modes, exactly what differentiates it from sibling video tools like create_craftstory2_video. The mode semantics (basic vs reference) make the tool's behavior 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?

It clearly describes when to use each mode ('basic': user_prompt + duration; 'reference': audio_clip_id for lip-sync), and notes that user_prompt is optional in reference mode. It doesn't route to sibling tools like create_craftstory2_video or upscale_video, but the mode conditions are explicit.

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