Skip to main content
Glama

Bounding Box

bounding_box
Read-only

Measure the axis-aligned or oriented bounding box of a shaped object in world coordinates, returning min, max, size, center and diagonal; enable tight mode to get mesh-verified dimensions.

Instructions

Axis-aligned bounding box (AABB) of a shaped object, mm, world coordinates. A measurement: returns numbers, creates nothing.

QUIRK (#284): min/max/size are OCC's ANALYTIC box, an UPPER bound. A trimmed face is boxed by its untrimmed carrier surface, so cuts through fillets, chamfers, lofts or spheres can report mm of material that isn't there (a real trim at X=-32.0 read -36.7). Before calling a part wrong-sized, check verified and pass tight=True.

oriented: also return the minimum-volume box at any orientation (OBB) under "oriented" (null if unsupported). Same analytic over-estimate. tight: also tessellate and return the mesh-derived box under "tight" — the trustworthy numbers. Opt-in: ~1.4s on a 200mm plate with 60 filleted holes. deflection: mesh chord tolerance mm for tight (default diagonal/2000, floor 0.001).

Returns {min, max, size, center ([x,y,z] mm, analytic), diagonal (mm), oriented (null | {size, center, diagonal}), verified, tight (null | {min, max, size, center, diagonal, deflection, triangles}), warnings (which face over-estimates, by how many mm)}. verified: "exact" (vertices touch all six faces) | "mesh_agrees" (tight found no disagreement) | "unverified" (usual on curved parts: upper bound only, re-run tight=True) | "over_estimate" (use "tight"; min/max/size wrong-big). The true box lies between "tight" and the analytic box.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "handle": "<handle>"
    },
    "name": "bounding_box"
  }
}

Input Schema

NameRequiredDescriptionDefault
tightNo
handleYes
orientedNo
workspaceNoRun this call in this named workspace
deflectionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.7
    • addedInput schema / properties / workspace
      Added value: +{
      +  "default": "",
      +  "description": "Run this call in this named workspace",
      +  "title": "Workspace",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnlyHint/openWorldHint; the description goes far beyond by disclosing the analytic over-estimate quirk (#284) with a concrete counterexample, the meaning of each `verified` value, and that the true box lies between tight and analytic. It also discloses the runtime cost of tessellation — exactly the behavioral context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the one-line purpose, then a labeled quirk block, then per-parameter and return blocks — easy to scan. It is dense and repeats the 'analytic over-estimate' idea several times (quirk, oriented, verified), which is mild redundancy but each restatement lands in a different section.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fully enumerates the return object including nested `oriented` and `tight` structures and `warnings`. Combined with the verification-state semantics and performance note, an agent has everything needed to call it and interpret the result correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (just `workspace`), so the description must carry the load and does: `oriented` (min-volume OBB, null if unsupported), `tight` (mesh-derived, opt-in cost), and `deflection` (chord tolerance, default diagonal/2000, floor 0.001) are all explained with defaults and tradeoffs. Only `handle` is left implicit, which is acceptable as the required object reference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource and coordinate/unit convention ('Axis-aligned bounding box (AABB) of a shaped object, mm, world coordinates') and immediately clarifies it is a read-only measurement, not a creation. That single line separates it from mutation siblings in the list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete conditional guidance: check `verified` and pass tight=True before declaring a part wrong-sized, and notes tight is opt-in and costs ~1.4s. It does not name alternative siblings (e.g. envelope_check, mass_properties, measure_distance) nor state when *not* to use this tool, so it stops short of full routing guidance.

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

Deploy Server

Other Tools