Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

photo_relief

Converts a photo into a printable relief sized for your specific printer, letting you set depth, style, and canvas dimensions for a part that prints as intended.

Instructions

Turn a photo into a relief made for the printer it will print on.

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": {
      "image_path": "<image_path>"
    },
    "name": "photo_relief"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo``deboss`` (carved in) or ``emboss`` (raised). Default: "deboss".
styleNoThe relief style: ``auto``, ``coin``, ``cameo``, ``etched`` or ``sketch``; the reply lists the accepted names when the one given is not a relief style. Default: "auto".
depth_mmNoRelief depth in mm (1.2-2.0 reads well). Default: 1.6.
layer_mmNoThe layer height the print will use; left out, 0.20 mm and the reply says so.
canvas_mmNoThe relief's width on the part, in mm. Default: 60.0.
nozzle_mmNoNozzle size; left out, the nozzle Kiln knows of, and the reply says which.
image_pathYesThe photo (PNG/JPG/HEIC).
mask_shapeNo``auto``/``circle``/``rectangle``/ ``rounded_rectangle``/``none`` -- the pool's outline. Default: "auto".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the agent knows this is a non-destructive, non-open-world operation. The description adds genuine context — output is fitted to the intended printer (which explains the nozzle_mm/layer_mm defaults) — but says nothing about what artifact is produced, where it lands, or whether it modifies an existing design.

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 photo-to-relief action leads. It is efficient, though it is terse enough that the assumed printer-fitting behavior has to be inferred rather than stated.

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

Completeness2/5

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

For an eight-parameter generation tool with no output schema, the definition leaves significant holes: what the result is (mesh, 3MF, saved design), where it is written, and whether it creates a new artifact or alters the current one are all unstated. The schema carries the defaults, but nothing carries the outcome.

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%, so every parameter including defaults, enum-like values, and fallback behavior for nozzle_mm and layer_mm is already documented in the schema. The description adds only the framing that these values are resolved against the target printer, which is useful but marginal.

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: turning a photo into a relief, with the added nuance that the relief is tailored to the target printer. It is clear this is a photo-driven relief generator rather than a generic texture applier like apply_image_texture, but it never names a sibling to distinguish itself explicitly.

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

Usage Guidelines2/5

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

There is no when-to-use guidance and no alternatives are mentioned. An agent wanting imagery on a part cannot tell from the description whether to pick photo_relief, apply_image_texture, or deboss_during_print; the only inference available is that a photo is involved.

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