to_cadquery

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the output is an editable, re-runnable script, the return includes parameters plus 'measured deviation of the script's output from the mesh', and an 'error' key signals out-of-vocabulary parts. Still missing: what the input model must be, whether the script is written to output_path, and what tolerance/validation is applied.

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?

Purpose is front-loaded in sentence one and the remaining text is dense capability scoping rather than filler. The repeated axis clauses ('along X, Y, or Z' three times) and deep parenthetical nesting make it a heavy read, but each clause constrains what geometry is supported, which is genuinely load-bearing.

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?

This is a conversion/generation tool with 3 undocumented parameters and no output schema. The description explains the shape of the return value but leaves the entire input contract (file type of input_path, meaning of tol and output_path, error handling for bad paths) unspecified — a significant gap for a tool the agent must invoke correctly on the first try.

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% for all three parameters, so the description must compensate and does not: input_path (required), output_path, and tol are never mentioned. The one concrete example ('hole_1_d = 6.0, extrude_len') describes the *output* parameters of the generated script, not the tool's inputs, so the agent gets no help on what file format input_path expects or what tol means.

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?

Opens with a specific verb+artifact: 'Write an editable parametric CadQuery script (.py) for a simple part.' The target format (CadQuery .py) inherently distinguishes it from siblings to_openscad and to_freecad, though it never names them. The capability vocabulary enumeration further pins down exactly what 'simple part' means.

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 long vocabulary list ('box/plate base with rectangular pads, holes... bosses... fillets...') plus 'Returns an "error" key when the part is outside that vocabulary' implicitly tells the agent when this tool will succeed versus fail. However, it never explicitly says when to pick this over to_openscad or to_freecad, or what to do on the error path.

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