ae_setKeyframeEase

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

Annotations already declare readOnlyHint=false, destructiveHint=false, so the agent knows this is a non-destructive mutation. The description adds the 'existing keyframe' precondition and the 0-100 influence domain, but does not say whether omitted ease fields are left untouched or reset, whether speed units are per-second, or what happens when the target keyframe is not found (errors silently?).

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?

A single dense fragment with the selector modes and value domains front-loaded; no filler. It is slightly telegraphic ('speedIn/Out' with no verb), but every clause carries information.

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 10-parameter mutation tool with no output schema and low schema coverage, the description covers the addressing modes and influence range but leaves speed semantics, partial-update behavior, and failure modes unexplained. Adequate to attempt a call, not adequate to call it confidently.

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 20% (layer and compositionName are the only documented properties), so the description has to compensate for 8 undocumented parameters. It does name the key ones and gives the influenceIn/Out 0-100 range, but speedIn/Out are named without units or meaning, and there is no guidance on whether `all:true` overrides time/keyIndex or how the two sides combine.

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: applies directional/asymmetric temporal ease to an existing keyframe, with the three addressing modes (time, keyIndex, all:true) called out. It is distinguishable from ae_setKeyframe (creation) and ae_setKeyframes (bulk), but it never names the very close sibling ae_setInterpolation, so the boundary between 'ease' and 'interpolation' is left for the agent to infer.

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?

"on an existing keyframe" implicitly tells the agent a keyframe must already exist and that this is a post-hoc adjustment, and the three selector modes are listed. But there is no explicit when-to-use vs. ae_setInterpolation / ae_setKeyframe / ae_setKeyframes, and no stated precedence when both time and keyIndex are supplied.

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