Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

verify_mesh_fit

Read-only

Check whether separate 3D parts physically assemble and whether a hinged part can turn, using exact shared-material math to measure penetration depth against a tolerance.

Instructions

Prove that separate parts can PHYSICALLY assemble, and that a hinged part can turn — the ONE fit check, exact shared-material math, not a picture.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "verify_mesh_fit"
  }
}

Input Schema

NameRequiredDescriptionDefault
jointNoA hinge to turn — ``"find"``, or ``moving`` / ``axis`` / ``pivot_mm`` / optional ``range_deg`` (see MOTION). Leave out for the one-pose fit check.
unitsNo``"auto"`` (default) / ``"mm"`` / ``"m"``. Default: "auto".
recipeNoOrganic recipe alternative to ``part_paths``.
part_pathsNoTwo or more mesh files, one per part, in assembled position (shared coordinate space).
tolerance_mmNoMax penetration depth that still counts as assembles-as-is (default 0.2). Default: 0.2.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.5.1
    • addedInput schema / properties / joint / description
      Added value: +"A hinge to turn — ``\"find\"``, or ``moving`` / ``axis`` / ``pivot_mm`` / optional ``range_deg`` (see MOTION).  Leave out for the one-pose fit check."
    • addedInput schema / properties / part_paths / description
      Added value: +"Two or more mesh files, one per part, in assembled position (shared coordinate space)."
    • addedInput schema / properties / recipe / description
      Added value: +"Organic recipe alternative to ``part_paths``."
    • changedInput schema / properties / tolerance_mm / description
      Previous value: -"Default: 0.2."New value: +"Max penetration depth that still counts as assembles-as-is (default 0.2). Default: 0.2."
    • changedInput schema / properties / units / description
      Previous value: -"Default: \"auto\"."New value: +"``\"auto\"`` (default) / ``\"mm\"`` / ``\"m\"``. Default: \"auto\"."
  2. Addedv1.5.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, destructiveHint:false, and openWorldHint:false, so the safety profile is covered. The description usefully adds that this is an exact numeric shared-material computation rather than a visual render, but it does not disclose what a result contains (pass/fail, penetration depths, joint sweep outcome) despite there being no output schema, nor does it mention cost or performance characteristics.

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?

A single tightened sentence with the core purpose front-loaded and the 'not a picture' contrast at the end. The capitalized PHYSICALLY and 'the ONE fit check' are slightly promotional, but they are doing real disambiguation work rather than padding.

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

Completeness3/5

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

For a five-parameter verification tool with nested objects and no output schema, the description establishes the concept well but leaves the return contract (what 'prove' yields, how tolerance violations are reported, what a joint sweep returns) entirely unstated. That is a meaningful gap for a tool whose whole value is a verdict.

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

Parameters3/5

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

The description reinforces the joint concept ('a hinged part can turn') in line with the schema, but it adds no syntax, format, or default detail for tolerance_mm, units, recipe, or the joint object. With schema description coverage at 100%, the schema already carries parameter meaning, so the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb-and-resource pair: 'Prove that separate parts can PHYSICALLY assemble' plus the hinge-turn extension. That distinguishes it from render/inspect siblings ('not a picture') and from measurement tools, but it never names a concrete alternative such as check_assembly_clearances or verify_mesh_measurements, so the differentiation is by implication rather than by name.

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

Usage Guidelines3/5

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

Usage is implied by the phrase 'the ONE fit check' and by the exclusion 'not a picture', which nudges the agent away from visual/render tools. However, there is no explicit statement of when to prefer this over the many sibling assembly and mesh-validation tools, and no prerequisites or when-not conditions are given.

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