Set scroll and fixed layers

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

Annotations already declare idempotentHint=true (which the description doesn't repeat, correctly), but the description adds real behavioural context beyond them: fixed layers are reordered to the top of the layer list, and instances won't have their layers moved at all. Editor support is disclosed with unverified surfaces flagged. It stops short of describing error/failure modes, but the mutation side effects are well covered.

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: the purpose and the two knobs come first, constraints and the sibling alternative follow. It is one dense paragraph rather than a list, and the clause about auto-layout/instance rules is tightly packed, but every sentence carries actionable 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?

No output schema exists, and the description covers what an agent needs for a 5-param mutation tool: effect on layer order, instance limitations, prerequisite for auto-layout, editor support, and the alternative tool for the adjacent behaviour. The retry/idempotency contract is handled by the idempotencyKey schema description.

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 80%, so much is already documented, but the description adds meaning the schema lacks: `fixedNodeIds` ordering ('bottom to top', '[] fixes none') and the empty-array sentinel, plus the instance caveat on `nodeId`. It enumerates the `overflow` values that are already in the enum, which is redundant but harmless.

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 ('Prototype scrolling for a frame') and immediately names the two controllable dimensions: `overflow` and `fixedNodeIds`. It explicitly distinguishes itself from figma_set_clips_content ('to cut content off on the canvas use...') and references figma_move_nodes for the absolute-positioning prerequisite, so an agent can place it among siblings 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 an explicit alternative and the condition that selects it: presentation behaviour here vs. canvas clipping in figma_set_clips_content. It also states when-not constraints (instances take `overflow` only and must be fixed in the main component; auto-layout frames need absolute positioning first) and the supported editors (Design; unverified FigJam, Slides).

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