find_faces

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

With no annotations, the description carries the burden and largely meets it: results are in TOP assembly coordinates, sub-assembly paths fan out across every part, and the `ref` format is shown verbatim. It omits anything about fan-out cost, ordering, or behavior on zero matches, and never states the read-only nature explicitly (only implied by 'find').

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, then scoping semantics, then a compact Args block — nothing is filler. The middle sentence is a dense run-on that packs path depth, coordinates, ref format and recursion into one line, which costs a little readability.

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?

An output schema exists, so return values need no prose, and all 8 params are covered across schema and description. What is left unstated is how filters combine (AND vs. override) and whether the result is coordinate-rich enough for constrain without a second lookup.

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 13%, so the description must compensate, and it does: it documents 7 of 8 params with meaning and concrete examples ([0,0,1] for an upward normal, {"Z": 182.5} for a center match, surface values "plane"/"cylinder"/"cone", empty-string = any). The one remaining param, `instance`, is already described in the schema.

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?

States a specific verb and resource (find faces) plus the exact filter axes: type, direction, position, size. The path/no-path split makes the scoping model explicit, which is enough for an agent to tell this apart from find_edges and from inspection tools like inspect_model.

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?

Explains the two operating modes (no `path` = active part, `path` = assembly component at any depth) and even names downstream consumers of the returned index/ref (create_sketch, sheet_metal_cut, constrain). It does not name explicit alternatives or say when *not* to use it, but the context for each mode is clear.

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