Skip to main content
Glama
zinin

sketchup-mcp2

by zinin

create_dovetail

Creates a dovetail joint between two boards in SketchUp with configurable angle, depth, width, height, and offsets, reporting boolean cut success.

Instructions

Create a dovetail joint between two boards.

All dimensions in millimeters; angle is in degrees, valid range (0, 60]. Offsets shift the joint from the board face's center. Defaults are sized for ~100 mm boards. The two boards must already touch/overlap along the joint axis.

Returns: JSON {tail: {id, name, type, bbox_mm|null}, pin: {...}, boolean_cuts: {attempted, failed}} — non-zero failed means some cuts did not apply (likely non-manifold geometry); verify via bbox_mm.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
angleNoDovetail flare angle in degrees, 0 < angle <= 60
depthNoJoint depth in mm
widthNoJoint width in mm
heightNoJoint height in mm
pin_idYesEntity ID from a previous response (integer or its string form)
tail_idYesEntity ID from a previous response (integer or its string form)
offset_xNoJoint offset from the board face's center along X, mm
offset_yNoJoint offset from the board face's center along Y, mm
offset_zNoJoint offset from the board face's center along Z, mm
num_tailsNoNumber of tails

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed17 schema fields changedv0.3.0
    • addedInput schema / properties / angle / description
      Added value: +"Dovetail flare angle in degrees, 0 < angle <= 60"
    • addedInput schema / properties / angle / maximum
      Added value: +60
    • addedInput schema / properties / depth / description
      Added value: +"Joint depth in mm"
    • addedInput schema / properties / height / description
      Added value: +"Joint height in mm"
    • addedInput schema / properties / num_tails / description
      Added value: +"Number of tails"
    • addedInput schema / properties / offset_x / description
      Added value: +"Joint offset from the board face's center along X, mm"
    • addedInput schema / properties / offset_y / description
      Added value: +"Joint offset from the board face's center along Y, mm"
    • addedInput schema / properties / offset_z / description
      Added value: +"Joint offset from the board face's center along Z, mm"
    • addedInput schema / properties / pin_id / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "minLength": 1,
      +    "type": "string"
      +  }
      +]
    • addedInput schema / properties / pin_id / description
      Added value: +"Entity ID from a previous response (integer or its string form)"
    • removedInput schema / properties / pin_id / minLength
      Removed value: -1
    • removedInput schema / properties / pin_id / type
      Removed value: -"string"
    • addedInput schema / properties / tail_id / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "minLength": 1,
      +    "type": "string"
      +  }
      +]
    • addedInput schema / properties / tail_id / description
      Added value: +"Entity ID from a previous response (integer or its string form)"
    • removedInput schema / properties / tail_id / minLength
      Removed value: -1
    • removedInput schema / properties / tail_id / type
      Removed value: -"string"
    • addedInput schema / properties / width / description
      Added value: +"Joint width in mm"
  2. First observedv0.0.1

TDQS

A4.2/5.0
Behavior4/5

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

No annotations exist, so the description carries full burden. It explains the return JSON structure, warns about non-manifold geometry causing failed cuts, and advises verifying via bbox_mm, but lacks side-effect details.

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?

The description is three sentences plus a bullet, front-loading the core purpose with no wasted words, perfectly sized for quick comprehension.

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?

Covers prerequisites, return structure, and unit context. For 10 parameters with full schema coverage and output schema, this is sufficient, though it could mention that the operation creates geometry.

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%, providing baseline 3. The description adds context beyond schema by specifying that dimensions are in mm, angle in degrees with valid range, offsets shift from board face center, and defaults suit ~100mm boards.

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?

The description clearly states it creates a dovetail joint between two boards, with specific details on units, angle range, offsets, and defaults, making the purpose unmistakable.

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?

It provides a prerequisite (boards must touch/overlap along joint axis) but lacks guidance on when to use this tool versus siblings like create_finger_joint or create_mortise_tenon.

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