Round the corners

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

Annotations already establish destructiveHint=true and readOnlyHint=false, so the mutation profile is known without the description. The description does add useful behavioral context by distinguishing uniform versus per-corner application. However, it does not disclose what happens when both 'radius' and individual corner parameters are supplied, whether existing radii are overwritten, or what occurs when called with only nodeId and no radius values. The annotation coverage lowers the bar, making 3 appropriate.

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 13-word sentence that front-loads the verb and packs both operating modes into minimal space. Every word earns its place with no boilerplate or repetition of schema fields. It is efficiently structured, though additional edge-case detail could still have been added without hurting conciseness.

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 6-parameter mutation tool with 33% schema coverage and no output schema, the description is under-specified. It omits edge-case behavior (mixing uniform and per-corner radii), node-type applicability (which Figma nodes support corner radius), and the effect of invoking with only the required nodeId and no radius values. An agent could call it incorrectly without further information.

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 description coverage is only 33% — nodeId and radius are described, while the four corner parameters have bare schema entries. The description partially compensates by mapping 'one radius for every corner' to the radius parameter and 'each corner on its own' to the four corner parameters, giving those undocumented params meaning. It does not clarify conflict resolution between uniform and per-corner inputs or units, so compensation is only partial.

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?

The description uses a specific verb ('Sets') with a clear resource (corner radius) and conveys the two operating modes: a single uniform value versus independent per-corner values. The title 'Round the corners' reinforces intent. It earns a 4 rather than 5 because sibling differentiation is implicit — no sibling is named — though no other sibling handles corner radius, so confusion risk is low.

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?

No when-to-use guidance, exclusions, or alternatives are provided. The description implies rounding corners but never states prerequisites (e.g., the node must support corner radius) or when to prefer this over sibling set tools like figma_set_bounds or figma_set_effects. An agent gets no help choosing among the many figma_set_* siblings.

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