convert

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

With no annotations, the description carries the disclosure burden and does well: it states that a file is written to output_path, that output_path defaults to input with .step suffix, that tol defaults to 0.1% of bbox diagonal, and it enumerates the returned fidelity report fields (method, faces, deviation, volume error). It does not cover overwrite behavior, failure modes, or units consistency.

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-loaded summary sentence followed by a tight Args block and a returns line; no filler, and each parameter note adds distinct information.

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 6-parameter tool with no output schema, the description covers inputs, defaults, and return contents well. Missing are overwrite semantics for an existing output file and what happens on failed fits, which an agent would want before invoking a write operation.

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%, so the description must compensate, and it does: every parameter gets a semantic gloss — tol as mesh noise in model units, the three boolean flags with concrete geometry examples (holes/bosses, domes, chamfers/countersinks), and default behaviors for both optional paths.

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 (convert) plus concrete source formats (STL/OBJ/PLY mesh) and target representation (STEP B-rep) with the fitted primitive types listed. This distinguishes it clearly from siblings like to_cadquery or to_openscad, which produce code rather than a STEP file.

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 input/output formats imply when to reach for it, but there is no explicit statement of when to prefer this over to_openscad/to_cadquery or when conversion is inappropriate (e.g. already-B-rep inputs). Usage is inferable rather than stated.

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