Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

inspect_mesh_view

Read-only

Render still PNG frames of a mesh from any camera pose, including orbit, comparison, deviation, and section views, so an agent can visually inspect geometry.

Instructions

Agent-side inspection camera: still PNG frames of a mesh from any pose, for YOUR eyes.

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": {
      "mesh_path": "<mesh_path>"
    },
    "name": "inspect_mesh_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo``view`` | ``orbit`` | ``compare`` | ``deviation`` | ``section`` (a cutaway; see ``section_frac``). Default: "view".
sizeNoTile size in pixels (256-1600). Default: 800.
zoomNoMagnification; >1 leans in (view mode). Default: 1.0.
focusNoOptional ``[x, y, z]`` to center the frame on.
yaw_degNoCamera spin around vertical (view mode). Default: 32.0.
mesh_pathYesPath to the mesh (STL / OBJ / 3MF / GLB).
pitch_degNoCamera tilt; negative looks down (view mode). Default: -18.0.
focus_regionNoPlain words naming where to lean in, from ``top``, ``bottom``, ``left``, ``right``, ``front``, ``back`` and ``center`` (``"top left"``). Read only when ``focus`` is not given; empty means none, and an unknown word is refused. Default: "".
section_fracNoHow deep into the part the cut plane sits, as a fraction from the camera side (``0.5``, the default, removes the front half). Read only in ``section`` mode. Default: 0.5.
reference_pathNoBEFORE/intent mesh (compare + deviation). Default: "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv1.5.1
    • addedInput schema / properties / focus / description
      Added value: +"Optional ``[x, y, z]`` to center the frame on."
    • changedInput schema / properties / focus_region / description
      Previous value: -"Default: \"\"."New value: +"Plain words naming where to lean in, from ``top``, ``bottom``, ``left``, ``right``, ``front``, ``back`` and ``center`` (``\"top left\"``).  Read only when ``focus`` is not given; empty means none, and an unknown word is refused. Default: \"\"."
    • addedInput schema / properties / mesh_path / description
      Added value: +"Path to the mesh (STL / OBJ / 3MF / GLB)."
    • changedInput schema / properties / mode / description
      Previous value: -"Default: \"view\"."New value: +"``view`` | ``orbit`` | ``compare`` | ``deviation`` | ``section`` (a cutaway; see ``section_frac``). Default: \"view\"."
    • changedInput schema / properties / pitch_deg / description
      Previous value: -"Default: -18.0."New value: +"Camera tilt; negative looks down (view mode). Default: -18.0."
    • changedInput schema / properties / reference_path / description
      Previous value: -"Default: \"\"."New value: +"BEFORE/intent mesh (compare + deviation). Default: \"\"."
    • changedInput schema / properties / section_frac / description
      Previous value: -"Default: 0.5."New value: +"How deep into the part the cut plane sits, as a fraction from the camera side (``0.5``, the default, removes the front half).  Read only in ``section`` mode. Default: 0.5."
    • changedInput schema / properties / size / description
      Previous value: -"Default: 800."New value: +"Tile size in pixels (256-1600). Default: 800."
    • changedInput schema / properties / yaw_deg / description
      Previous value: -"Default: 32.0."New value: +"Camera spin around vertical (view mode). Default: 32.0."
    • changedInput schema / properties / zoom / description
      Previous value: -"Default: 1.0."New value: +"Magnification; >1 leans in (view mode). Default: 1.0."
  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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the output is still PNG frames (a static render, not a live stream) and that it is agent-facing, but it does not say whether the images are returned inline or as file paths, or whether there are cost/latency implications for an agent's context.

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 front-loaded sentence with no filler; the core purpose lands immediately. It is arguably too terse for a 10-parameter tool with five modes, but nothing in it is wasted.

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?

With 100% schema coverage and read-only annotations, most of the burden is carried elsewhere, and no output schema exists, so the description should ideally say what an agent gets back (inline image vs path). It also says nothing about the compare/deviation modes needing reference_path, leaving the call-context incomplete for a moderately complex 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 every parameter, including the five modes and the section_frac/focus_region interactions, is documented in the schema. The description adds no parameter meaning beyond that, 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?

The description states a concrete verb and resource: it renders still PNG frames of a mesh from any pose. "Agent-side ... for YOUR eyes" implicitly separates it from user-facing render tools such as render_design_mesh or show_on_stage, but it never names a sibling the way a top-scoring definition would.

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 phrase "for YOUR eyes" suggests the agent should call this when it needs to look at the mesh itself rather than to show the user something, but the description gives no explicit when-to-use, when-not-to-use, or alternative tools (cross_section_view, compare_renders, visualize_model). Usage is only implied.

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