silhouette_add_rectangle

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

Annotations declare this is a non-read-only, non-destructive, non-idempotent mutation, and the description adds genuine behavior beyond them: corner_radius_mm is clamped to half the smaller side, rotation_deg rotates clockwise about the rectangle's center, and layer defaults to CUT with SCORE and PERF as alternatives. It still omits what happens on failure, whether repeated identical calls duplicate shapes, and what handles come back from the mutation.

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?

Three compact sentences that front-load the anchor geometry and then layer in radius, rotation, and layer defaults, with no filler. The parenthetical enumeration "(or 'SCORE', 'PERF')" is slightly crammed, 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?

For a 9-parameter, 0%-schema-coverage mutation tool with no output schema, the description leaves notable holes: the required design parameter is never explained and nothing indicates whether a shape id or handle is returned for later transform_shape or remove_shape calls. The geometry semantics are well covered, but the object-creation contract is incomplete.

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 0%, so this dimension must be driven entirely by the description, and the description does heavy lifting: it defines the anchor semantics for x_mm/y_mm, the units and clamping rule for corner_radius_mm, the rotation axis and direction for rotation_deg, and the allowed values and default for layer. Among the 9 parameters only design and label go completely undefined, and width_mm/height_mm are self-evident from their names and the clamping rule. The description compensates well for otherwise undocumented parameters.

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 ('Add a rectangle') and pins the anchor geometry to the top-left corner at (x_mm, y_mm), which is enough to distinguish it from sibling shape tools like silhouette_add_circle or silhouette_add_polygon. It does not explicitly compare against siblings such as the box template or polygon tools for rectangular use cases, so it stops short of a 5.

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?

The description never says when to use this versus alternatives (e.g., add_box_template or add_polygon) and gives no preconditions, such as needing an existing design to add the rectangle into or what units/coordinate space x_mm and y_mm operate in beyond the mm suffix. The only guidance is the implicit layer default.

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