Skip to main content
Glama

set_printer_model

Tell Kiln which printer model a saved printer is -- by name, or from a slicer file.

Instructions

Tell Kiln which printer model a saved printer is -- by name, or from a slicer file.

Kiln checks every print against the bed it will land on and the
temperatures the machine can take, and slices with the model's own
profile.  All three are read from the printer's model.  With no model
set, those checks are SKIPPED.  Use this as soon as ``kiln_health`` or a
log says the model is not configured.

Two ways to say it -- give exactly one:

* ``printer_model``: any name the catalogue recognises (``"Bambu Lab
  A1"``, ``"bambu_a1"``, ``"MK4"``, ``"K1 Max"``).
* ``slicer_file``: a project the user saved from Bambu Studio,
  OrcaSlicer or PrusaSlicer (File > Save Project), or a printer
  settings file exported from one.  It already names the printer it
  was set up for.  Ask a new user for one instead of asking them to
  look up a model key.

A printer that is NOT in Kiln's catalogue can still be set up, but only
from a slicer file: the file states its bed, which is the one fact Kiln
cannot do without.  Kiln then saves the printer on this machine with
that bed and its own generic limits (never a limit read from the file),
lays slices out on that bed and measures designs against it.  It has no
tuned profile for such a printer and will not move its head.  A name
alone for a printer outside the catalogue is refused (``UNKNOWN_MODEL``,
with the closest matches); ask for the slicer file.

Args:
    printer_model: The model, in any spelling the catalogue knows.
    slicer_file: Path to a saved slicer project or exported settings.
    printer_name: The saved printer to set.  Omit for the active one.
    replace: Allow changing a printer that already has a different
        model, or taking a newer file's bed for a printer set up from
        an earlier file.  Off by default: the model decides the limits
        Kiln checks against, so a wrong one is worse than none.

Returns ``applied`` (whether anything changed), the ``printer``, its
``printer_model`` and ``in_catalogue``, and a ``message`` to relay.
From a slicer file it also returns ``file`` -- the printer, bed, nozzle
size and material the file states -- and ``notes`` where the file's bed
or nozzle differs from what Kiln holds.  The notes change nothing:
relay them, and if the file's nozzle is the one fitted, record it.

Nothing is written for a model that does not suit the printer's
connection, or over another model unless ``replace`` is set.  Limits an
owner typed for a printer are never written over.

Input Schema

NameRequiredDescriptionDefault
replaceNoDefault: false.
slicer_fileNo
printer_nameNo
printer_modelNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.0

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so: it warns that checks are SKIPPED without a model, explains what happens for out-of-catalogue printers, names the UNKNOWN_MODEL refusal, and states that owner-typed limits are never overwritten and nothing is written unless replace is set.

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?

Long, but front-loaded with the purpose and organized with bullets for the mutually exclusive inputs. A few passages repeat the catalogue-versus-file distinction, but almost every sentence adds operational value for a tool with this much conditional behavior.

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

Completeness5/5

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

No output schema exists, so the description documents returns itself: applied, printer, printer_model, in_catalogue, message, plus file and notes from a slicer file, and how to relay notes. Error and edge-case behavior is also covered, leaving no obvious gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25%, and the description compensates for every parameter: printer_model accepts any spelling with concrete examples, slicer_file names the source applications and file types, printer_name defaults to the active printer, and replace's exact semantics and default are spelled out.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Tell Kiln which printer model a saved printer is") with the two accepted input forms. It is clearly distinct from sibling tools like register_printer, list_printer_variants or select_printer_variant.

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

Usage Guidelines5/5

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

Explicitly says when to act: "Use this as soon as kiln_health or a log says the model is not configured." It also gives alternatives and routing advice — ask a new user for a slicer file rather than a model key, and use the slicer file when the printer is outside the catalogue.

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