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

With no annotations, the description carries the full behavioral burden, and it does well by disclosing async-by-default behavior, pollUrl/videoUrl, the blocking override, native audio generation, and pricing. However, 'Returns an 8-second 720p clip' is stated as fixed even though the schema exposes durationSeconds and a 1024p resolution option, so it slightly overstates the default output.

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 compact, front-loaded with the core purpose, and every sentence adds value: output format, use cases, prompt strategy, async behavior, and cost. It avoids redundancy and is easy for an agent to scan.

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 covers the essential runtime behavior—default output, async flow, polling, blocking mode, audio considerations, and cost—without an output schema to rely on. It does not detail authentication, error cases, or the full set of param interactions, but the schema already documents the parameters and the core workflow is sufficiently complete.

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 coverage is 100%, so the baseline is 3. The description adds meaningful prompt guidance—include sound cues since audio is generated from the scene—and clarifies the default duration and resolution. This goes beyond the schema's field descriptions, particularly for the prompt 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 opens with a specific verb and resource: 'AI video generation from a text prompt.' It further clarifies the output—an 8-second 720p clip with native audio—and lists concrete use cases such as b-roll, product shots, and social clips. This makes it clearly distinct from sibling tools agent_image and create_music.

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 provides clear usage context by listing short-form video, b-roll, product shots, music-video visuals, social clips, and ads. It does not explicitly name when not to use this tool or contrast it with agent_image and create_music, but the video-specific framing makes the intended scope clear.

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