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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, closed-world), so the description only needs to add behavior beyond that. It adds useful easing semantics and the important note that an empty list clears keyframes, but omits a key behavior: whether setting a prop's keyframes replaces the existing set or merges with it, and what happens to keyframes on other props.

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?

Front-loaded with purpose, then packed parentheticals that define prop and ease without wasted sentences. Density is high but each clause carries information; only the ease enumeration is long-winded.

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 4-parameter mutation with no output schema, the description covers prop and ease thoroughly but leaves the core mutation contract underspecified: replace-vs-append behavior and what the response looks like. Those are the details an agent most needs before calling it.

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 only 25%, so the description has to compensate and mostly does: it defines units and meaning for every prop enum value (px offset from centre, scale multiplier, degrees, 0..1 opacity) and enumerates the ease vocabulary including cubic-bezier syntax and its 0..1 constraint on x. Remaining gaps are clipId (undocumented anywhere) and confirming the units of keyframe v, but the semantic load is well carried.

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?

"Animate a clip property over time" is a specific verb+resource with the supported clip types named (video, image, text, overlay). The sibling add_keyframe / remove_keyframe / clear_keyframes exist but the description never contrasts itself with them, so differentiation is left to inference.

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?

Usage is implied rather than stated: the plural "keyframes" array plus "Empty list clears" hints at bulk-set and clear semantics, which loosely routes against add_keyframe and clear_keyframes. There is no explicit when-to-use/when-not guidance or prerequisite (e.g. whether the clip must exist, which project).

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