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

Annotations only cover the safety profile (non-read-only, non-idempotent, non-destructive, closed-world), while the description adds real behavioral context: background/asynchronous preparation, reuse of in-flight work, three transient candidates, a picker that updates on completion, and that nothing persists until an explicit selection. It stops short of describing lifecycle details such as picker expiry or re-invocation cost.

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 key behavior (three transient candidates, picker returned, selection required to persist) is front-loaded in the first two sentences, and the parameter notes are compressed into one closing sentence. It is dense but nearly every clause carries information; 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?

For a six-parameter, asynchronous generation tool with an output schema and full annotation coverage, the description supplies the essentials: transience, async completion, and the save boundary. Missing only peripheral detail such as picker URL lifetime or what repeated invocation does to in-flight preparation.

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 every parameter is already documented, making 3 the baseline. The description adds a little meaning for replaceVariantId (it applies only after the new selection saves) and states that selectedScreenshotPaths restricts candidate inputs, but much of this restates the schema's own wording.

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 names a specific verb and resource: it starts or reuses preparation of three transient promo-video candidates and returns an embedded picker or its URL. That is far more specific than the title, though it never names the natural siblings (preview_promo_video, get_promo_video_generation, apply_promo_video_candidate) to draw the boundary explicitly.

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 workflow is implied ('Only an explicitly selected candidate becomes a saved variant', replaceVariantId only with explicit user approval), which tells the agent this is a non-committal preparation step. However, there is no explicit when-to-use-this-vs-that guidance against preview_promo_video or get_promo_video_generation, so the agent must infer the routing.

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