sketch_create

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

With no annotations, the description carries the full burden and does substantial work: it discloses the sketch-space coordinate model, the returned transform, a concrete axis pitfall on origin:XZ, a named failure mode (details.reason = "face_not_planar"), and the effect of project_edges. It omits preconditions and side effects such as whether an active document is required, whether the sketch becomes the active edit target, or whether a timeline feature is created.

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?

Front-loads the one-line purpose, then groups coordinate semantics, pitfall, failure mode, return shape, and a usage example with no filler. The XZ-axis warning is unusually verbose for a description but is precisely the detail that prevents wrong-geometry calls.

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?

No output schema exists, so the description's explicit return payload ({"sketch": {ref}, "name", "plane", "component", "transform"}) is necessary and present, and error behavior is documented. What is missing is the surrounding workflow context (active document assumption, interaction with sketch_list/sketch_get after creation).

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 100%, so a 3 is the baseline, but the description adds real meaning beyond the schema: it explains plane ref syntax by example, clarifies that project_edges only applies to face-based sketches and changes the result ('clean sketch unless project_edges=true'), and shows name usage. Component is left unaddressed in prose.

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 2D sketch') plus the exact set of valid placements (origin plane, construction plane, planar face). This clearly distinguishes it from siblings such as sketch_draw (which adds geometry inside a sketch) or construction_plane.

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 example line 'sketch_create(...) then sketch_draw(sketch=<ref>)' establishes the correct ordering relative to the sibling sketch tool, and the note that a non-planar face fails with INVALID_PARAMS tells the agent which inputs to avoid. It stops short of explicit 'use this instead of X when Y' routing, so it is not a 5.

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