Skip to main content
Glama
sketchup-mcp2

sketchup-mcp2

by zinin

fillet_edge

Rounds every straight feature edge of a SketchUp group or component to a specified radius and segment count, skipping curved, rim, and concave edges automatically.

Instructions

Round (fillet) every straight feature edge of a group/component by radius mm with segments arc segments.

Skips seams of curved surfaces (edges where the surface bends by less than 25°: the two face normals differ by under 25°) and the rims of curved surfaces, such as a cylinder's top and bottom circles: fillet cannot round a tessellated curve. Also skips concave (inside-corner) edges, such as the base of a post or the inner corner of an L-shaped block: rounding them would need added material. A body with no straight feature edges (cylinder, cone, sphere) fails with -32602, as does an inside-out body (faces pointing inward): reverse its faces first. A call starts no new cut after 30 s inside SketchUp and then rolls back, changing nothing. Unreliable on non-manifold geometry.

Returns: JSON {id, name, type, bbox_mm|null, edges_filleted, stats{attempted, succeeded, subtract_failed, skipped_no_match, skipped_seam, skipped_concave, skipped_curved}} — check stats.subtract_failed == 0 (failed cuts) and stats.skipped_no_match == 0 (edges consumed by earlier cuts).

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": {
      "id": "<id>"
    },
    "name": "fillet_edge"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesEntity ID from a previous response (integer or its string form)
radiusNoFillet radius in mm
segmentsNoArc segments per rounded edge, 1–32

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.4.0
    • changedInput schema / properties / segments / description
      Previous value: -"Arc segments per rounded edge"New value: +"Arc segments per rounded edge, 1–32"
    • removedInput schema / properties / segments / exclusiveMinimum
      Removed value: -0
    • addedInput schema / properties / segments / maximum
      Added value: +32
    • addedInput schema / properties / segments / minimum
      Added value: +1
  2. Changed6 schema fields changedv0.3.0
    • addedInput schema / properties / id / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "minLength": 1,
      +    "type": "string"
      +  }
      +]
    • addedInput schema / properties / id / description
      Added value: +"Entity ID from a previous response (integer or its string form)"
    • removedInput schema / properties / id / minLength
      Removed value: -1
    • removedInput schema / properties / id / type
      Removed value: -"string"
    • addedInput schema / properties / radius / description
      Added value: +"Fillet radius in mm"
    • addedInput schema / properties / segments / description
      Added value: +"Arc segments per rounded edge"
  3. First observedv0.0.1

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does: a 30 s in-SketchUp cut budget with full rollback, a -32602 failure mode for bodies with no straight feature edges and for inside-out bodies, a remediation hint (reverse faces first), and an unreliability warning on non-manifold geometry. It even tells the agent which stats counters to validate after the call.

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?

Front-loaded with the core action, then failure and return-value details in descending priority — good structure. Minor waste in the self-restating parenthetical 'edges where the surface bends by less than 25°: the two face normals differ by under 25°'.

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?

Despite an output schema existing, the description adds the interpretive layer the schema cannot: what each skip counter means and the invariant that subtract_failed and skipped_no_match must both be zero. Combined with the timeout and geometry-precondition notes, an agent has everything needed to call this correctly and to interpret a suspicious result.

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 id, radius, and segments are already documented including units and the 1–32 range. The description restates 'radius mm' and 'segments arc segments' without adding meaning such as how segment count trades off against file size or cut time. Baseline 3 applies.

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 specific verb+resource+scope: round (fillet) straight feature edges of a group/component by a given radius and segment count. That is concrete enough to act on. It never names the obvious sibling chamfer_edge, so nothing in the text routes the agent between the two bevel-like operations.

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

Usage Guidelines4/5

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

Gives strong implied usage boundaries by enumerating what is skipped (seams under 25°, curved rims, concave edges) and which bodies fail outright (cylinder, cone, sphere, inside-out). What's missing is explicit routing to alternatives — e.g. 'use chamfer_edge when you want a flat bevel' — so the agent must infer the choice.

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