Set corner radius

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

Adds substantial context beyond annotations: partial failure semantics (one node failing does not fail the call), the return payload shape, and editor support (Design verified; FigJam/Slides unverified). Annotations already cover idempotency and non-destructive nature. The description still doesn't clarify whether this mutates the underlying component or only instances, but the failure and environment details are valuable.

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-loads the main action and modes in the first sentence, then layers failure semantics and editor support. Dense but each clause carries operational information. Slightly overloaded with the return-shape example, which could live in an output schema, but no sentence is wasted.

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?

Covers mode selection, smoothing semantics, partial-failure behavior, and environment support. With six parameters and no output schema, the description fills the gap for return values and failure handling. It doesn't explain the interaction between radius and radii (which wins if both are supplied), leaving a small correctness gap.

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 100%, so each parameter is documented in the schema itself. The description reiterates the corner order and the smoothing squircle value (0.6), adding minor user-oriented context beyond the raw schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (Round) and resource (corners of nodes), and immediately disambiguates the two mutually exclusive modes (radius vs radii) with a per-corner array shape. An agent can distinguish this from siblings like figma_resize_nodes or figma_set_auto_layout without opening the 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?

Notes that `radii` applies to frames and rectangles and that `smoothing` can be set alone, which implies usage constraints. However, it gives no explicit guidance on when to prefer this tool over alternatives like figma_set_auto_layout or figma_set_constraints for corner-adjacent properties, nor any exclusion criteria.

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