draw_donut

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains the filled nature and the special case of inner_dia=0, but it does not disclose whether the donut is created on the current layer, how the fill is rendered (e.g., hatch or solid?), or any interaction with existing entities or coordinate systems. The lack of safety or mutation info is a gap for a drawing tool.

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?

The description is a single, highly efficient sentence that conveys the essence of a donut and clarifies an edge case. Every word earns its place without redundancy.

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?

While the tool is simple and has a small parameter set, the absence of annotations and output schema (actually an output schema exists, but the description doesn't need to explain return values) means the description covers the core geometry but lacks placement context (e.g., current layer, coordinate system) and any drawing conventions. It is adequate for a basic drawing primitive but not complete for an agent unfamiliar with CAD conventions.

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%, so the description must add meaning beyond parameter names. It explains the key relationship between inner_dia and outer_dia and the boundary case for inner_dia=0. However, it leaves cx, cy, and layer meanings implicit — though cx/cy are universal coordinate parameters and layer is standard, so a baseline of 3 is appropriate.

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 identifies the tool as drawing a donut (filled ring) and clarifies the relationship between inner and outer diameter, distinguishing it from similar shape tools like draw_circle or draw_arc. However, it doesn't explicitly name the sibling alternatives, so it doesn't fully differentiate from the draw_circle or draw_ellipse family.

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 implies usage by defining the geometry (inner_dia=0 gives a filled dot) but does not state when to prefer this over draw_circle, draw_arc, or hatch_circle. There is no explicit when-to-use or alternative guidance, only contextual hints about the parameter semantics.

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