apply_still

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

No annotations are provided, so the description must disclose consequences. It does not state whether applying a still overwrites existing grades, is reversible, or what happens if the still/clip name is invalid, leaving the safety profile incomplete.

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?

Single sentence, front-loaded with the action and resource, no wasted words.

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?

The tool is small and the main invocation logic is covered, but as a mutation without annotations it lacks side-effect/failure details and any mention of prerequisites (e.g., a saved still must exist). Still, it is adequate for basic invocation.

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?

With 0% schema coverage, the description compensates by explaining both parameters: still_name is a name and clip_name is optional with a current-clip default. This adds meaningful semantics beyond the schema's field titles, though it doesn't describe value formats or constraints.

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 uses a specific verb ('Apply') and identifies the resource ('a still (grade) to a clip by name'), clearly distinguishing it from sibling save_still. It also immediately states the default behavior for unspecified clip.

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 indicates the primary context: applying a saved grade to a named clip, with fallback to the current clip. However, it does not explicitly contrast with save_still or other color tools, though the workflow is implicit.

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