add_hole

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

With no annotations, the description carries the load well: it discloses the return payloads (`dimensions`, `hole`, mass properties) and the non-obvious side effect that thread='modeled' produces a real printable thread rather than a cosmetic one. It omits that the operation mutates/removes material from the active body and any preconditions (e.g. requires an existing part), which for a cut feature is a meaningful gap.

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 with the verb, then organized as scannable bullets each keyed to an argument pattern. It is long, but justified for a 13-parameter, three-mode tool; the density of the first bullet (coordinate aside plus hole spec) 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?

For a 13-param tool with zero schema coverage and no output schema, this covers the modes, geometry semantics and return shapes that an agent actually needs. Missing pieces are the destructive/mutating nature of the cut, the unexplained `name` parameter, and any failure conditions — minor but real for a modeling 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% and 13 parameters exist, so the description must compensate — and it does: it explains 12 of 13 parameters with real semantics, including the shared coordinate system (40x20 profile centre = x=20,y=10), face string values ('+z', '-x'), depth semantics (through vs blind), the fit/thread/iso enumerations and their effects. Only `name` is left unexplained.

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+resource ("Cut a round hole") and immediately partitions the tool into three distinct operating modes. It also anchors the coordinate system to a named sibling (add_box), so an agent can tell exactly what geometry this produces versus cut_slot, cut_profile or cut_offset_pocket.

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?

Strong intra-tool routing: each bullet names the argument combination that selects it (diameter+xy = through hole, face+z_mm = face-anchored, cbore_* = counterbore, iso= = Hole Wizard), plus an explicit preference rule ("Prefer iso= for standard fasteners"). It never states when to choose this over sibling cut tools (cut_slot, cut_profile), so it stops short of full when/when-not coverage.

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