sw_loft

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

Annotations only declare readOnlyHint=false and destructiveHint=false, which already tells the agent this mutates the model, so the description is free to add other context — yet it says nothing about feature creation, whether the resulting feature is added to the tree, or what the cut/surface/thin modes do to the result. For a 10-parameter feature-creating operation this leaves significant behavioral gaps.

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?

A single front-loaded sentence that names the operation first and the use cases second, with no filler or restatement of the tool name.

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?

With 10 parameters, several behavior-altering flags (cut, surface, closed, tangency), and no output schema, the description is far too thin — it never explains what the resulting feature is, how the mode flags change the outcome, or what happens on failure.

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?

The phrase 'profiles on different planes' reinforces the required ordering constraint, but that constraint is already in the schema. Schema coverage is 70%, and the undescribed parameters (cut, start_tangency, end_tangency) are exactly the ones where loft behavior is easiest to get wrong; the description supplies no guidance on any of the 10 options.

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?

A specific verb ('loft') and resource ('profiles on different planes') plus concrete example outcomes (wings, fuselages, blades, duct transitions) make the operation recognizable and separate it from siblings like sw_sweep or sw_extrude. It stops short of naming those alternatives explicitly, so no 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 geometric examples imply the scenario (skin a shape between dissimilar cross-sections), which lets an agent infer when lofting beats extruding or sweeping. But there is no explicit 'use this when… / use sw_sweep instead when…' statement and no prerequisites.

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