measure

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

With no annotations, the description carries the full burden and does supply real behavioral context: units are mm and degrees, parts are addressed by lowercase name without .prt, each feature call either commits or rolls back, and nothing persists without model_save. That said, the lead sentence claims the tool 'Creates/edits geometry', which contradicts its read-only measurement nature and could mislead an agent about side effects.

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 second paragraph is tight and front-loaded with the actual operation. The first paragraph, however, is shared plugin boilerplate that occupies roughly half the text, does not describe measuring, and actively misdirects with its 'Creates/edits geometry' opener — content that does not earn its place in this tool's definition.

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?

There is no output schema, and the description does name the return values (distance, two closest points, angle), which is the key compensation. It omits result units for distance beyond the general mm statement, and says nothing about failure behavior when the refs are invalid or the geometry has been rolled back.

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 33%, so the description must compensate, and it does so partially by restating the accepted forms (surface:N, edge:N, axis:N, datum name, or [x,y,z] model point) and by clarifying that the angle is only returned when both operands are planes or straight lines. It does not clarify whether the two operands may mix types (point vs surface) or what happens with degenerate inputs, so the coverage gap is not fully closed.

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 second paragraph states a specific operation: minimum distance between two refs or points, returning distance, closest points, and angle for planar/straight-line pairs. However, the description opens with 'Creates/edits geometry... through the DreamFeatureApp plugin', which misdescribes a read-only measurement tool and buries the actual purpose in a boilerplate preamble. An agent reading top-down would initially misclassify this as a modeling operation.

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?

'Use it to check a result' gives an implied usage context, reinforced by the earlier pointer to model_info (volume, bound_box) and preview_image as verification tools. There is no explicit statement of when-not to use it or how it differs from list_dimensions/find_geometry for the same verification job, so the agent must infer the boundaries.

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