generate_video

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

No annotations are provided, so the description carries the full burden; it does disclose that jobs are durable and async by default, which is genuinely useful. However, it omits what the tool returns (job id), what permissions or Flow session state are required (despite flow_browser_login existing as a sibling), and what happens on failure. Several behavioral gaps remain for a task-submitting write operation.

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 sentences, zero filler, with the action and the async behavior both front-loaded before any nuance. Nothing here could be removed without losing information.

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?

With 12 parameters, no annotations, and no output schema, the description needs to say more than it does. Most critically, it never mentions how to follow up on an async job (get_video_job, get_video_status, cancel_video_job all exist as siblings) or that output lands under outputs/<job-id>/. That omission leaves a real workflow gap 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?

Schema description coverage is 100%, so the schema already explains model, duration, negativePrompt, referenceImagePaths, and the deprecated outputPath. The description adds only the conceptual framing that the prompt is treated as a director brief, which enriches the meaning of the primary parameter. Baseline 3 is appropriate.

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 and resource ("Create a durable Google Flow video job") plus the pipeline it triggers: director brief interpretation and prompt compilation. That is clearly distinct from list/status/delete siblings, but it never names how it differs from refine_video, regenerate_video, or flow_browser_generate_video, which an agent could 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?

The phrase "processed asynchronously by default" implies when the immediate-return mode applies, and the schema's waitForCompletion default reinforces it, but the description never states when to pick this tool over refine_video, regenerate_video, or generate_image. Usage is only implied, not routed.

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