cut_opening

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

With no annotations, the description carries the full burden and does so richly: idempotency guard (refuses on existing opening), snapping tolerance (~3.5mm), a single undo step, an internal classify_point self-check with its result reported, and the composed world transform for nested walls. These are exactly the non-obvious traits an agent needs before invoking a destructive geometry operation.

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?

Long but dense and front-loaded — the core action and its output geometry lead, followed by behavioral caveats. Every sentence conveys a distinct fact (nesting, from_floor, refusal, snapping, self-check, undo, frame, units), though the run-on density slightly hurts scanability.

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?

Despite no output schema, the description explains what is produced (face topology) and that the self-check result is reported. Combined with 89% schema coverage and 9 parameters, an agent has enough to call this complex tool correctly without further documentation.

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 89%, so the schema already documents most params, but the description adds real meaning: from_floor's face-splitting behavior, the optional U-shaped frame build, and the units convention ('all lengths and coordinates are in metres') which the schema omits. This goes beyond the baseline expected at high coverage.

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+resource with geometric detail: cut a rectangular opening (door/window) through a wall, producing holes in both faces plus reveal faces. This clearly distinguishes it from the inverse sibling fill_opening and from generic face tools like create_face.

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?

Gives clear operating context: works on nested groups at any depth, refuses if an opening already exists (cannot double-cut), and from_floor:true selects the no-sill variant. It does not explicitly name alternatives such as fill_opening or push_pull, so it stops short of full when/when-not routing.

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