Skip to main content
Glama
Anycubic Slicer MCP

Anycubic Slicer MCP

Find the best orientation

find_best_orientation
Read-onlyIdempotent

Ranks a model’s bed orientations by support area, height, bed contact, weak layers, and fit before slicing, returning rotation values to use with slice_model.

Instructions

Rank the ways a model can lie on the bed by support area, height, bed contact, weak layers and fit.

Use it before slicing a part whose orientation isn't obvious; pass the winner's rotation to slice_model as rotation_deg. For load-bearing parts, analyze_strength also recommends walls and infill. Works on the mesh alone without running the slicer. Read-only.

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": {
      "model": "<model>"
    },
    "name": "find_best_orientation"
  }
}

Input Schema

NameRequiredDescriptionDefault
topNoHow many ranked orientations to return, 1 to 12.
goalNo'balanced', 'least_support', 'fastest', 'strongest' or 'best_bed_adhesion'.balanced
modelYesPath to an STL, OBJ, 3MF or STEP file on this computer.
printerNoPrinter preset name or a unique part of it, e.g. 'Kobra X'. Omit to use the printer selected in the slicer window.
load_axisNoDirection the part is pushed or pulled in use, in model coordinates: 'x', 'y', 'z' or [x, y, z]. Used by goal='strongest'.
support_angleNoOverhang angle in degrees from vertical that needs support, 10 to 80.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.1

TDQS

A4.6/5.0
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 trailing 'Read-only' is redundant. The genuinely additive fact is 'works on the mesh alone without running the slicer', which tells the agent this is a cheap geometric analysis with no slicer dependency. It stops short of noting cost or whether a printer profile materially changes results.

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?

Four short sentences, front-loaded with what the tool does, then when to use it, then the hand-off details. Nothing is padding except the final 'Read-only', which merely restates the annotations.

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?

With no output schema, the description usefully implies the return value by telling the agent to pass the winner's rotation as rotation_deg, and the top parameter governs result count. It does not sketch the remaining returned fields (scores per criterion, fit/weak-layer warnings), leaving a small gap for a ranking tool that returns structured comparisons.

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 100%, so the baseline is 3, but the description adds real meaning: the five ranking criteria map onto the goal options (least_support, fastest, best_bed_adhesion, strongest), and the mention of load-bearing parts signals when load_axis matters. It still doesn't explain the top/support_angle interplay beyond what the schema already says.

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 ('rank the ways a model can lie on the bed') and enumerates the ranking criteria (support area, height, bed contact, weak layers, fit). It is clearly distinguishable from slice_model and analyze_strength, which are named as downstream steps rather than competitors.

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?

Gives an explicit trigger ('use it before slicing a part whose orientation isn't obvious', which also implicitly scopes out parts where orientation is obvious) and routes the agent onward: rotation_deg to slice_model, analyze_strength for load-bearing parts. This is close to full when/when-not/alternatives coverage.

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