Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

record_proven_recipe

Mark a design version's print recipe as proven after a successful print, or record failures with notes so future agents avoid repeating them.

Instructions

Record a design version's recipe as proven after a print (Pro).

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": {
      "design_id": "<design_id>",
      "decoration_type": "<decoration_type>",
      "product_type": "<product_type>"
    },
    "name": "record_proven_recipe"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNoNotes about the print outcome (required for failures — describe what went wrong so future agents can avoid it). Default: "".
successNoTrue if the print succeeded, False if it failed. Default True. Pass False to record failures for diagnostics. Default: true.
versionNoSpecific version number to mark. Omit for latest.
materialNoThe material it printed in, if not in the recipe.
design_idYesDesign directory name (e.g. ``kiln-ashtray``).
parametersNoExplicit parameter dict. Omit to auto-extract from the design's recipe file.
printer_nameNoThe printer it printed on; its model and nozzle are read from what Kiln holds for it. Omit for the one printer Kiln knows of.
product_typeYes``ashtray``, ``frisbee``, ``planter``, etc.
filament_lineNoThe filament's line (``PLA Basic``, ``PLA Matte``) when the person knows it; never guessed.
decoration_typeYes``logo_deboss``, ``photo_emboss``, ``text_deboss``, or ``qr_code``.
nozzle_diameter_mmNoThe nozzle size, if not on record.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv1.5.1
    • addedInput schema / properties / decoration_type / description
      Added value: +"``logo_deboss``, ``photo_emboss``, ``text_deboss``, or ``qr_code``."
    • addedInput schema / properties / design_id / description
      Added value: +"Design directory name (e.g. ``kiln-ashtray``)."
    • addedInput schema / properties / filament_line / description
      Added value: +"The filament's line (``PLA Basic``, ``PLA Matte``) when the person knows it; never guessed."
    • addedInput schema / properties / material / description
      Added value: +"The material it printed in, if not in the recipe."
    • changedInput schema / properties / notes / description
      Previous value: -"Default: \"\"."New value: +"Notes about the print outcome (required for failures — describe what went wrong so future agents can avoid it). Default: \"\"."
    • addedInput schema / properties / nozzle_diameter_mm / description
      Added value: +"The nozzle size, if not on record."
    • addedInput schema / properties / parameters / description
      Added value: +"Explicit parameter dict.  Omit to auto-extract from the design's recipe file."
    • addedInput schema / properties / printer_name / description
      Added value: +"The printer it printed on; its model and nozzle are read from what Kiln holds for it.  Omit for the one printer Kiln knows of."
    • addedInput schema / properties / product_type / description
      Added value: +"``ashtray``, ``frisbee``, ``planter``, etc."
    • changedInput schema / properties / success / description
      Previous value: -"Default: true."New value: +"True if the print succeeded, False if it failed. Default True. Pass False to record failures for diagnostics. Default: true."
    • addedInput schema / properties / version / description
      Added value: +"Specific version number to mark.  Omit for latest."
  2. Addedv1.5.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare a non-read-only, non-destructive, closed-world mutation, so the description's main job is to add mutation-specific context. It adds the 'proven' semantics and the post-print timing, but never mentions that failures can also be recorded (the schema's success=False path), which makes the description narrower than the actual behavior.

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, and the key scope ('after a print') arrives immediately. The trailing '(Pro)' is slightly cryptic but costs almost nothing.

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?

For a record-write tool with no output schema, the schema itself carries the required inputs, defaults, and fallback behaviors (auto-extract parameters, omit version for latest), and the description supplies the intent. It would be stronger if it noted the failure-recording path and the Pro requirement explicitly.

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 one of the 11 parameters is documented in structured fields with defaults and examples. The description adds no parameter-level meaning beyond the schema, which is the expected baseline here.

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 names a specific verb and resource ('Record a design version's recipe as proven') and anchors it in time ('after a print'), which separates it from siblings like get_proven_recipe and list_proven_recipes. The '(Pro)' marker also signals a tier gate, though it is not explained.

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 'after a print' implies the trigger condition, and the read-side siblings make the write scope inferable. However, there is no explicit statement of when not to call it, whether it can be called repeatedly for the same version, or what alternative to use if a recipe should be un-marked.

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