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

With annotations already declaring readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=true, the description still adds two facts not present in structured data: the operation consumes AI credits, and it is asynchronous, returning a job handle rather than a finished asset. It does not explain the destructiveHint=true flag, but nothing in the text contradicts it.

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, front-loaded with the action and artifact, followed by the two operationally important facts (credit spend, async polling). Every clause earns its place.

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 zero-required-param, fully documented generation tool with an output schema, the description covers the essentials: what is produced, that it costs credits, and how to retrieve the result. The remaining gap is sibling differentiation, which the description leaves to the reader.

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% with all five parameters (mood enum, prompt, workspaceId, idempotencyKey, durationSeconds bounds) documented inline, so the schema does the heavy lifting. The description adds no parameter-level detail beyond what is already there; baseline 3 applies.

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 gives a specific verb and resource: "Queue a background music track into the BlitzReels media library," which is distinct from generation_video_create, generation_image_create, generation_sound_create, and generation_voiceover_create by naming the artifact type. It stops short of explicitly contrasting itself with the nearest sibling (generation_sound_create), so an agent must infer the boundary.

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?

It provides the follow-up step ("returns a job to poll with generation_jobs_get"), which is useful workflow context, but gives no condition for choosing this over generation_sound_create or the other generation_* tools, and no exclusions. Usage is implied by the artifact type rather than stated.

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