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

Annotations only declare the generic write profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). The description adds information annotations cannot convey: the call consumes credits, requires explicit user confirmation of specific fields, and is asynchronous so results must be polled from list_jobs and read from final video_url.

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?

Three tight sentences: identity first, the high-stakes credit/confirmation warning second, the polling instruction last. Nothing is redundant and the most important operational constraint is front-loaded rather than buried.

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?

For a 14-parameter mutation tool with no output schema and thin schema descriptions, the description covers the queue-then-poll lifecycle and the cost gate but not the input modes implied by image_url, end_image_url, source_video_url, and reference_images. An agent would not know from the text alone whether this is text-to-video, image-to-video, or video extension.

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 only 21% across 14 parameters, so the description must compensate and it only partly does: it enumerates provider, prompt, duration, resolution, aspect ratio, and audio. Model, image_url, end_image_url, source_video_url, reference_images, negative_prompt, and workspace_id remain undocumented anywhere beyond their names and enums.

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 ('Queue an AI video job') and names the concrete backends (Google Veo 3.1, xAI Grok Imagine Video 1.5), so the agent knows this is asynchronous video generation. It also routes status checks to list_jobs, though it does not distinguish itself from nearby siblings like generate_image, get_video_options, or run_video_function.

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 an explicit precondition workflow: confirm provider, prompt, duration, resolution, aspect ratio, audio, and credit cost with the user before calling, and it names the follow-up tool (list_jobs with type=video). It does not state any when-not-to-use conditions or explain when a different generation tool would be preferred.

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