Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

build_organic_mesh

Create a freeform organic 3D mesh from a blended primitive recipe and open an interactive preview for orbiting, zooming, and iterating on the design.

Instructions

Build a freeform/organic mesh from a smooth-blended primitive recipe. 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": {
      "recipe": "<recipe>"
    },
    "name": "build_organic_mesh"
  }
}

Input Schema

NameRequiredDescriptionDefault
partsNoWhen True, emit one solid per primitive ``"group"`` + run the fit check + return an assembled preview. Default: false.
recipeYesThe recipe as a JSON object: ``name``, ``resolution`` (grid cells across the longest axis, 40-280), optional ``smooth_mm`` / ``mirror`` / ``shell_mm``, and ``primitives``, a list of ``{"type": ..., ...}`` entries (sphere, ellipsoid, capsule, tapered_capsule, torus, arc, rounded_box, ring_stack) with the per-type fields and per-primitive options the tool description lays out.
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: "".
output_dirNoOptional directory for the per-part STLs when ``parts=True``. Omitted, the set lands in ``<system temp>/kiln_organic/<recipe name>/`` — for the same reason ``output_path`` has a guessable default: a part set is the slowest build here and the likeliest to outrun the call. Either way the directory holds one ``<group>.stl`` per part plus ``_assembled.stl``, the assembled preview, which is kept beside its own parts rather than orphaned in a temp file. Default: "".
output_pathNoOptional STL output path for the single-mesh mode. Omitted, the mesh lands at ``<system temp>/kiln_organic/<recipe name>.stl`` (an anonymous temp file when the recipe names nothing usable); the same name overwrites, which is what iterating on one subject should do. Default: "".
reference_imagesNoPath (or list of paths) to the image(s) the user is asking you to reproduce. Pass on every iteration, not just the first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 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 / output_dir / description
      Previous value: -"Default: \"\"."New value: +"Optional directory for the per-part STLs when ``parts=True``.  Omitted, the set lands in ``<system temp>/kiln_organic/<recipe name>/`` — for the same reason ``output_path`` has a guessable default: a part set is the slowest build here and the likeliest to outrun the call.  Either way the directory holds one ``<group>.stl`` per part plus ``_assembled.stl``, the assembled preview, which is kept beside its own parts rather than orphaned in a temp file. Default: \"\"."
    • changedInput schema / properties / output_path / description
      Previous value: -"Default: \"\"."New value: +"Optional STL output path for the single-mesh mode.  Omitted, the mesh lands at ``<system temp>/kiln_organic/<recipe name>.stl`` (an anonymous temp file when the recipe names nothing usable); the same name overwrites, which is what iterating on one subject should do. Default: \"\"."
    • changedInput schema / properties / parts / description
      Previous value: -"Default: false."New value: +"When True, emit one solid per primitive ``\"group\"`` + run the fit check + return an assembled preview. Default: false."
    • addedInput schema / properties / recipe / description
      Added value: +"The recipe as a JSON object: ``name``, ``resolution`` (grid cells across the longest axis, 40-280), optional ``smooth_mm`` / ``mirror`` / ``shell_mm``, and ``primitives``, a list of ``{\"type\": ..., ...}`` entries (sphere, ellipsoid, capsule, tapered_capsule, torus, arc, rounded_box, ring_stack) with the per-type fields and per-primitive options the tool description lays out."
    • addedInput schema / properties / reference_images / description
      Added value: +"Path (or list of paths) to the image(s) the user is asking you to reproduce.  Pass on every iteration, not just the first."
  2. Addedv1.5.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so safety is covered. The description adds genuinely new behavior: it opens an interactive inline 3D stage, hosted sessions attach a browser stage link, oversized meshes are auto-decimated for the stage, and the PNG preview is described as the floor rather than the full result.

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

Conciseness3/5

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

The stage behavior is stated twice — once parenthetically in the opening paragraph and again at length in the 'INLINE 3D STAGE' section — so the text repeats itself. The ALL-CAPS headers aid scanning but the duplicated content costs space without adding information.

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

Completeness4/5

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

There is no output schema, and the description compensates by explaining what the user sees on success (inline stage, browser link fallback, decimated mesh, PNG preview). The nested recipe object's shape is delegated to a thorough schema entry, so the definition is close to complete for a 6-parameter build tool.

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?

Schema description coverage is 100%, and the recipe parameter's schema entry already lays out name/resolution/primitives and the per-type fields. The description adds no parameter-level meaning beyond that, so the baseline 3 is appropriate when the schema does the heavy lifting.

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 first sentence gives a specific verb and resource: 'Build a freeform/organic mesh from a smooth-blended primitive recipe.' It names related tools (design_session, compile_scad), so an agent gets some differentiation, but it never contrasts itself with the many other mesh-composition siblings (compose_part_from_primitives, build_parametric_prompt, etc.).

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 gives routing context, but it points at compile_scad as 'the make → preview → iterate loop,' which muddies rather than clarifies when this tool itself is the right choice. There is no explicit statement of when to prefer build_organic_mesh over compile_scad or the primitive-composition siblings.

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