generate_video

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

No annotations are provided, so the description carries full behavioral burden. It discloses that it runs in the Kuudo deployment (remote), render times from 11 seconds to minutes, background vs. pending behavior for task-capable clients, the idempotency/resume mechanism, the warning not to retry with a new recovery_id after unknown submission, and the result format (signed URLs and agent-iris://videos/vid_N handles). This is exceptionally transparent.

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?

The description is long but front-loaded with the core purpose and input types. Each sentence adds essential information: constraints, async behavior, recovery, compliance. It is structured and not wasteful, though it could be tightened by moving some operational details to the skill reference. Still, given the tool's complexity, the length is justified.

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 13 optional parameters, no output schema, and no annotations, the description covers all necessary aspects: input formats, constraints, timing, async handling, recovery, compliance, and result format. It also directs to the skill for deeper mode/model selection. Nothing an agent needs to call it correctly is missing.

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%, so the schema already documents each parameter. The description adds cross-parameter constraints (references/1080p/4k require 8 seconds, inputs must be bounded handles or http(s) URLs, never inline data) that are not fully captured per-parameter. This adds meaningful semantic value beyond the schema.

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 clearly states the tool generates video with Google Veo 3.1 from text, images, frames, reference images, or video extension. It names the specific resource and action, and the verb 'generate' distinguishes it from sibling tools like generate_image and generate_openai_image. The scope is precise.

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 description directs agents to read the canonical skill://amazon-video/SKILL.md before planning or generating, covering mode/model selection and compliance. It also explains async behavior with get_video_status and recovery_id. However, it doesn't explicitly say 'when not to use this' versus alternatives like generate_image, leaving that inference to the agent, though the skill reference partially compensates.

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