Skip to main content
Glama

construct_print

Read-onlyIdempotent

Converts a valid v2 scene or parameter document into a watertight 3MF or STL for 3D printing, with checks for bed fit, thin walls, overhangs and required supports.

Instructions

One watertight body of a valid v2 scene or parameter document, to 3D print: 3MF (default) or binary STL, base64, in millimetres, Z up, on the bed; with the checks (watertight, separate pieces, fits the bed, overhangs that need supports, what was thickened) and the scale.

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": {
      "document": "<document>"
    },
    "name": "construct_print"
  }
}

Input Schema

NameRequiredDescriptionDefault
fitNothe largest print that stands on the printer's bed
joinNogaps between parts up to this wide are closed, in mm (default 1.6)
sizeNothe longest side in mm (default 100)
wallNoopen surfaces thickened to this wall in mm (default 0.8)
exactNo3MF: the construct's own solids, parts of one object the slicer joins; only open and too-thin surfaces become voxels
linesNothe parts drawn only in lines: none, engrave (cut in) or raised (true)
scaleNoprint at 1:N of the real size instead
detailNothe voxel size in mm (default 0.4)
formatNo
printerNoa printer class: its bed, finest voxel and thinnest wall
documentYesa construct-scene (version 2) or a construct-params document
compare_printersNoinstead of a print: for each printer class, the largest print and how much detail survives

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered and the description is not contradicting anything. It adds genuinely useful behavioral context: the returned payload is base64 geometry in millimetres, Z-up and bed-centred, and it reports a list of checks (watertight, separate pieces, bed fit, support-needing overhangs, thickened surfaces) plus scale. It does not say what happens on an invalid document or an unprintable model, which is the remaining gap.

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

Conciseness5/5

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

A single dense sentence with the primary output and format decisions front-loaded before the parenthetical checks list. There is no filler; every clause (format, encoding, units, orientation, checks, scale) carries information an agent needs.

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 12-parameter tool with a nested document object and no output schema, the description does a fair job of naming what comes back (geometry plus checks plus scale). It falls short only on failure behavior and on the alternate compare_printers return shape, which lives solely in the schema.

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

Parameters4/5

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

Schema coverage is already 92%, so the baseline is 3, but the description goes further by fixing the defaults and semantics the schema leaves implicit: 3MF is the default format, output is binary STL if requested, units are millimetres, orientation is Z-up and on the bed. That is real added meaning rather than a restatement of the parameter list.

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 concrete verb (construct one watertight body) applied to a specific resource (valid v2 scene or parameter document) with the exact deliverables (3MF default or binary STL, base64, mm, Z up, on bed). An agent can tell this is the print-output tool rather than a compile/validate/export step, though it never explicitly contrasts itself with construct_export.

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?

Usage is implied by 'to 3D print' and the required 'document' parameter, and one mode switch is signposted ('instead of a print' for compare_printers). There is no explicit statement of when to choose this over construct_export or construct_compile, nor any note that the input document must first be valid.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.