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

Annotations only declare the generic mutation profile (readOnly=false, idempotent=false, destructive=false). The description adds high-value specifics beyond that: no credit spend, the frame is cut by the renderer (async, hence polling get_storyboard), and the operation is a single undo step — exactly the operational traits an agent needs.

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?

Four tight sentences, front-loaded with the core action, then prerequisites, cost/async behavior, and undo granularity. Every sentence adds information an agent can act on.

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?

With an output schema present, return values need no explanation, and the description covers the remaining unknowns: cost, prerequisite state, asynchronous completion, and undo scope. Nothing needed to invoke it correctly is missing.

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 0%, so the description must carry the burden, and it does: it explains that `scene` receives the still and `from_scene` is the source that must already have a clip. `storyboard_id` is left implicit, which is a minor gap but easily inferred.

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 ('give a scene a still that is the LAST frame of another scene's clip') plus the intent (the next shot picks up where the previous ended). This clearly distinguishes it from siblings like extract_video_frame, generate_scene_images, and match_scene_motion.

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 a hard prerequisite: `from_scene` must already carry a clip, generated or uploaded, and tells the agent to poll get_storyboard for the still to land. It does not explicitly name competing tools to avoid, so it falls short of a full when/when-not/alternatives statement.

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