Remove keyframes (Motion)

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

Annotations only cover safety flags, and the description adds real behavioral detail beyond them: non-animated fields surface in `notAnimated` rather than erroring, each removal is read back after Figma settles and retried, a stuck track fails INTERNAL with `partial.notRemoved`, and returned `removed`/`remaining` are read-back values. It also discloses that animation styles are untouched and the strict-mode gating.

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 the core action and scope before the failure/retry and prerequisite clauses. Dense but nearly every clause carries operational information; only the closing editor-support list is marginal.

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?

No output schema exists, yet the description describes the return shape (`removed`, `remaining`) and failure payloads, plus the prerequisite and retry model. For a mutation with no output schema, nothing an agent needs to call 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?

With 75% schema coverage the schema already documents `fields`, `session` and `idempotencyKey`; the description adds the semantics the schema omits — that omitting `fields` removes every track, and that fields are named as figma_get_motion_context names them. No value added for `nodeId`, but the omission behavior is the key gap the schema leaves open.

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 ('Remove a layer's manual keyframe tracks') with scope ('the given `fields`, or every track when omitted'), and explicitly marks the boundary against the sibling that writes tracks ('figma_set_keyframes writes tracks'). An agent can route this without opening any schema.

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 concrete preconditions: under BRIDGE_PROCESS=strict this returns PROCESS_REQUIRED until the session has read the motion skill via figma_get_guide and the frame has a plan via figma_set_motion_plan, and it names figma_set_keyframes as the counter-operation. It stops short of an explicit when-not-to-use statement, but the prerequisite chain is unusually actionable.

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