katto_dub_clip

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

With annotations that are all negative hints (readOnly/openWorld/idempotent/destructive all false), the description carries the behavioral burden — and it delivers: it discloses that the operation is free and does NOT use video quota, that each call starts a fresh render (elaborating idempotentHint=false), and that the caller must poll katto_get_rerender for the result. No contradiction with annotations; the description adds genuine context beyond the structured hints.

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?

Four compact sentences, each contributing a distinct fact: purpose and languages, cost/quota behavior, non-idempotency, and the poll-for-result contract. There is minor redundancy — the language list echoes the schema enum and '(not idempotent)' restates idempotentHint=false — but overall the description is tight and front-loaded with the core purpose.

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 3-parameter, all-required, async tool with no output schema, the description covers the essential call flow an agent cannot infer: the call returns a rerender_id and requires polling katto_get_rerender, and it consumes no video quota. The main gap is the unaddressed relationship with the closely named katto_rerender_clip, leaving a selection ambiguity for the agent.

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?

The schema documents id ('Job id') and clip_index ('0-based clip index') but leaves languages with only an enum and no prose. The description compensates by enumerating the 8 languages and specifying 'one or more,' and it adds meaning to the other parameters by establishing that they refer to a finished clip. At 67% schema coverage, the description bridges the gap in the least-documented parameter.

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?

The description states a specific action — re-rendering a finished clip with a dub in one or more of 8 named languages — and adds distinctive constraints (free, not idempotent, returns rerender_id). This clearly identifies the tool's job, though it stops short of explicitly contrasting with the sibling katto_rerender_clip, so sibling differentiation is by implication rather than by name.

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?

The phrase 'one finished clip' implies a precondition: the tool operates only on completed clips, which gives the agent some usage context. However, the description never states when to prefer this over katto_rerender_clip or katto_create_clip_job, nor does it name alternatives or exclusions — the key sibling distinction is left to inference.

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