h3_generate

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

With no annotations, the description carries the full burden, and it does disclose the key trait: this is asynchronous and non-blocking, returning a job_id rather than a result. It omits cost/credit implications (a real concern for video generation and relevant given the h3_art_quote sibling), expected duration, and whether queued jobs can be cancelled via h3_cancel_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?

A single dense sentence with the async return behavior front-loaded alongside the purpose. Nothing is padded or repeated.

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 six-parameter generation tool with zero schema descriptions, no output schema, and no annotations, one sentence leaves too much unsaid: no guidance on parameter tradeoffs, no follow-up workflow, no mention of cost. Only the async contract is adequately covered.

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% across 6 parameters, so the description must compensate and it does almost nothing: 'text-to-video' hints that prompt is a text description, but seed, steps, width, height, and frames receive no mention at all. An agent cannot tell from this text that resolution, frame count, or step count are controllable.

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 ('Queue'), names the exact model and modality ('MiniMax H3 text-to-video clip with generated stereo audio'), which is far beyond a restatement of the name. It does not, however, distinguish itself from h3_art_generate, the sibling an agent would most plausibly confuse it with.

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?

'Queue' plus 'returns job_id immediately' implies the async pattern and points a careful agent toward h3_job_status / h3_download_video, but that is inference rather than guidance. There is no explicit statement of when to pick this over h3_art_generate or what to do after receiving job_id.

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