Generate

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, so the safety profile is covered. The description usefully adds the async/polling behavior for video, which annotations cannot express, but omits significant behavioral traits such as cost/quality implications of the default 'poor' tier and any rate or duration limits.

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 tight sentences with the core action front-loaded and the polling caveat immediately after. Every clause carries information an agent needs; there is no filler.

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?

Return values need not be explained because an output schema exists, and the async flow is described. However, for a 10-parameter, no-schema-description tool, the missing explanation of tier defaults, output modes, aspect ratios, and durations leaves the definition short of 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 description coverage is 0% across 10 parameters, so the description carries the full burden and does not meet it. It only clarifies job_id (poll to resume) and media_type (image vs video), leaving tier, model, provider, output_mode, aspect_ratio, duration_seconds, and reference_image_url completely undefined.

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 ('Generate an image or video from a text prompt') and even subdivides by media type, so the agent knows exactly what the tool produces. It does not explicitly differentiate itself from the sibling tools (understand, help, config), but those are clearly different domains, so the risk of confusion is low.

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?

Gives clear operational context for the video path: the first call returns a job_id and subsequent calls with job_id poll for completion. There is no explicit when-not guidance or comparison to alternatives, but no real alternative generation tool exists among the siblings.

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