Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

import_model_parts

Import a multi-part 3D model while preserving named parts, then open an interactive 3D stage to orbit, zoom, and inspect the result.

Instructions

Import a MULTI-PART model with its named parts intact. Opens Kiln's interactive inline 3D stage on the result (orbit/zoom panel in MCP Apps hosts; hosted sessions add a browser stage link). MAKE DOORS: design_session, Kiln's front door for making an object, is not installed here (signed in to Kiln it runs on Kiln's servers). On this install compile_scad IS the make → preview → iterate loop: make it, show the preview, iterate.

INLINE 3D STAGE: on success this tool opens Kiln's interactive 3D stage — an inline viewer panel the user can orbit, zoom, and turn over — in hosts that render MCP Apps panels (Kiln's hosted connection attaches a browser stage link for hosts that don't). Oversized meshes are decimated automatically for the stage; the PNG preview is the floor, not the whole experience.

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": {
      "model_path": "<model_path>"
    },
    "name": "import_model_parts"
  }
}

Input Schema

NameRequiredDescriptionDefault
brief_idNoThe saved goal's id from ``design_session``, so this make is recorded against the goal and checked against it. Empty when there is no goal. Default: "".
design_idNoOptional design to record the source file under as a version, so the adoption is on record. Every caller gets every part and the full manifest; when the version cannot be recorded for this caller the response says so in ``version_skipped``. Default: "".
model_pathYesScene-bearing file (GLB/glTF/3MF best). A single-mesh file still adopts as one part.
output_dirNoWhere part STLs land (default: temp). Default: "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.5.1
    • changedInput schema / properties / brief_id / description
      Previous value: -"Default: \"\"."New value: +"The saved goal's id from ``design_session``, so this make is recorded against the goal and checked against it. Empty when there is no goal. Default: \"\"."
    • changedInput schema / properties / design_id / description
      Previous value: -"Default: \"\"."New value: +"Optional design to record the source file under as a version, so the adoption is on record.  Every caller gets every part and the full manifest; when the version cannot be recorded for this caller the response says so in ``version_skipped``. Default: \"\"."
    • addedInput schema / properties / model_path / description
      Added value: +"Scene-bearing file (GLB/glTF/3MF best). A single-mesh file still adopts as one part."
    • changedInput schema / properties / output_dir / description
      Previous value: -"Default: \"\"."New value: +"Where part STLs land (default: temp). Default: \"\"."
  2. Addedv1.5.0

TDQS

B3.2/5.0
Behavior3/5

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

Beyond the annotations the description does add genuine behavior: the tool opens an interactive 3D stage as a side effect, oversized meshes are automatically decimated, and a PNG preview is always produced. That is useful disclosure the structured fields do not carry. It still omits operational traits such as whether the source file is modified, how long import takes, or whether failure leaves partial STLs behind.

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

Conciseness2/5

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

The purpose is front-loaded, but the inline-3D-stage behavior is stated twice — once in the opening paragraph and again in a dedicated "INLINE 3D STAGE" block — and the all-caps "MAKE DOORS" section is largely tangential to invoking this tool. Roughly half the text could be removed without losing invocation-relevant information.

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?

There is no output schema, so the description should say what comes back; instead it only advertises the viewer and preview, leaving the parts list and manifest unmentioned in the description (they surface only incidentally inside a parameter's schema text). For a four-parameter import with a side effect, the description covers the experiential result but not the returned data.

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?

With 100% schema description coverage, the schema already explains `brief_id`, `design_id`, `model_path`, and `output_dir`, including defaults. The description adds no parameter-level meaning at all and even duplicates schema territory (the inline stage and browser stage link appear in both). Baseline 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?

The opening clause gives a specific verb and resource: importing a multi-part model with named parts intact, which distinguishes it from single-mesh importers. However, the differentiation effort is spent on `design_session`/`compile_scad` (the "make" path) rather than on the file-import siblings an agent would actually weigh it against, such as `import_external_mesh`, `import_step_file`, or `extract_model_from_3mf`.

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?

The "MAKE DOORS" paragraph implies this tool is for adopting existing multi-part files rather than authoring geometry, and points to `compile_scad` as the make → preview → iterate loop on this install. But it never states the positive trigger condition explicitly ("use this when you have a GLB/3MF scene and want parts preserved") nor excludes any of the many competing import tools in the sibling list.

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