create_sketch

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

With no annotations, the description carries the full burden. It discloses key geometry behavior: how face_index overrides plane, the 1-based face indexing, and offset direction conventions per plane. However, it does not state document-state requirements, side effects such as whether the sketch becomes active, or error conditions.

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 primary action is front-loaded in the first sentence, followed by an Args section that is dense and free of repetition. Every clause conveys operational meaning, including the per-plane offset direction shorthand.

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?

An output schema exists, so return values need not be described. The description covers the non-obvious geometry semantics of all three primary parameters and delegates instance selection to the schema. It stops short of stating document prerequisites or whether the new sketch becomes the active sketch, which would matter for a mutation tool with no annotations.

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 only 25%, but the description compensates strongly: it supplies plane enum values, explains the 0 sentinel for face_index, defines offset units and sign convention per plane, and clarifies the plane/face precedence. The remaining instance parameter is already documented in the schema.

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 ('Create a new sketch') and enumerates the three supported placement targets: work plane, body face, or offset work plane. This distinguishes it clearly from sibling drawing tools such as draw_rectangle and draw_circle.

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?

Explains the selection logic between plane and face_index ('Ignored if face_index > 0') and points to list_faces() for locating a face. It also gives a concrete use case for offset ('For ribs/bosses at a height'), though it does not explicitly state prerequisites such as needing an active part document.

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