Create Video

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

Annotations only say the tool is not read-only and not destructive, so the description carries the behavioral disclosure burden. It surfaces two non-obvious facts: the call starts an asynchronous job that only returns an id, and it costs money. Both are exactly the kind of hidden behavior an agent needs before calling a paid, async generation endpoint.

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?

Two dense sentences carry all the essential information: action and endpoint first, then the critical follow-up behavior and cost warning. There is no filler, repetition of the schema, or unnecessary detail.

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?

The description is complete for a complex, paid, asynchronous tool: it identifies the job-based workflow, tells the agent how to track the result, and warns about cost. An output schema exists, so the description doesn't need to explain return values, and parameter details are already in the input schema.

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 100%, with each parameter already well documented, so the baseline is 3. The tool description adds no per-parameter semantics, but it also doesn't need to repeat what the schema already provides.

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 opens with a concrete verb and resource ('Start a Kenari video job') and names the exact endpoint, which clearly identifies the tool's role. It is immediately distinguishable from read/status siblings like get_video_status and wait_for_video, and from image-focused siblings.

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 gives clear context for when to call this tool: when starting a new video generation job. It also tells the agent what to do after invocation, poll via get_video_status/wait_for_video. It does not explicitly contrast with alternatives like extend_video or generate_image, but the phrase 'video job' plus the sibling names makes the intended usage unambiguous.

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