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

There are no annotations, so the description carries full behavioral burden. It does add genuine value by disclosing the billable cost ('1 credit per call'), the unit convention (mm), and the artifact set produced (DXF, STL, SVG, 3D viewer, mass/specs). However it is silent on what 'host it' concretely means — persistence, returned URLs, artifact lifetime, or failure modes for invalid parameter combinations.

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 long but front-loaded with the core verb and outputs, then organizes the bulk into a single dense part-to-parameter mapping that is genuinely necessary given nine disjoint part schemas. Every clause carries information; it only loses a point for the run-on enumeration being harder to scan than a structured list.

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?

For a 4-parameter tool with 0% schema coverage, nested free-form params, and no annotations, the description covers generation well but leaves real gaps: how the hosted artifacts are retrieved, whether `title` matters, how `material` affects output, and when this differs from the other cad_* tools. It is adequate to invoke the tool, but not to invoke it confidently in a crowded tool family.

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% and `params` is a free-form object, so the description does the heavy lifting by documenting the expected keys for every enum value of `part` (e.g. gear {module, teeth, thickness, bore}, flange {outer_diameter, bore, bolt_circle, bolts, bolt_diameter, thickness}). It does not mark which per-part keys are required versus optional or supply defaults, which would have earned a 5.

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?

Names a specific verb+resource ('Generate a precise parametric part') and then enumerates all nine part types with their parameter sets, so an agent knows exactly what family of geometry this tool produces. It is clearly distinguishable from siblings like cad_calc (computation only) or cad_reverse (reverse engineering) even without opening any other schema.

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 never states when to pick this tool over cad_build, cad_fusion, cad_machine, cad_ideas, or arch_design — a dense sibling cluster where routing matters most. It only implies usage through the enumeration of part types, with no prerequisites, alternatives, or exclusions given.

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