silhouette_add_polygon

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

Annotations already declare this as a non-read-only, non-idempotent but non-destructive local write, so the safety profile is covered. The description contributes genuine behavioral semantics beyond that: the valid side range (3-64) and the orientation convention that rotation_deg=0 puts one vertex up. It omits what happens with an out-of-range sides value, whether the shape is appended to an existing design or a selection, and what is returned.

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?

Two sentences, zero filler, with the core geometry front-loaded before the orientation note. Every clause carries information an agent cannot get from the schema.

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?

The geometric core is complete, but for a mutation tool with no output schema the description never says what is returned (e.g. a shape handle), nor what 'design' and 'layer' mean or that the design must pre-exist. With 0% schema coverage on 8 parameters, those omissions leave the agent guessing on three of them.

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 0% across 8 parameters, so the description must carry the load. It does explain cx_mm, cy_mm, radius_mm, sides (range) and rotation_deg (orientation), but leaves design, label and layer entirely undefined — notably layer, whose default 'CUT' implies meaningful domain semantics that are never explained.

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 regular polygon') and pins the geometry precisely: inscribed in a circle of radius_mm, centred at (cx_mm, cy_mm), with a 3-64 side constraint. That shape description is enough to tell it apart from sibling shape creators such as add_circle, add_ellipse and add_star 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?

There is no when-to-use guidance: no statement about when a polygon is preferable to a circle/rectangle/star, no prerequisites (e.g. that the referenced design must already exist), and no routing to alternatives. The agent must infer all selection logic from the tool name alone.

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