Skip to main content
Glama
ToungaGH

SketchUp MCP for SketchUp Make 2017

by ToungaGH
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

audit_geometry

Inspect SketchUp groups for geometry flaws such as open or non-manifold edges, duplicate edges, tiny or non-planar faces, and near-coincident vertices.

Instructions

Check a group (or every top-level group, if 'group' is omitted) for geometry problems: stray edges (0 faces), open edges (1 face), non-manifold edges (>2 faces), duplicate edges (same endpoints, separate edge entities — the cause of 'deleting a line deletes the wall'), near-coincident vertex pairs (<2mm, different vertex objects), tiny faces (<0.005 m², reported with the nested group they live in, counted per group in tiny_faces_by_group; faces inside closed solids such as frame end faces are skipped and only counted), non-planar faces, and mergeable coplanar seams (same material/orientation). Always recurses into nested groups. Each issue category is capped at 50 example items plus a total count. Without 'group', only the counts per group are returned (pass details:true for the example items too, which can be very long); audit one group to see where its issues are. Duplicate edges and near-coincident vertices carry a cross_group flag (the two sit in different groups: inherent and harmless) with separate counts. All lengths and coordinates are in metres.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
groupNoGroup name to audit; omit to audit every top-level group. Found at any nesting depth: a top-level group with this name wins, otherwise the name must be unique in the model (an ambiguous name is refused, listing the matches).
detailsNoWhole-model audit only: include example items, not just counts (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0+make2017

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the 50-item cap plus total counts, unconditional recursion into nested groups, the cross_group flag semantics, which faces are skipped (closed-solid end faces) and that they are still counted, and that all units are metres. It stops short of failure/permission behavior, but the operational disclosure is unusually rich.

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

Conciseness3/5

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

Front-loads the purpose, and each clause is informative, but it is delivered as one long run-on paragraph dense with em-dash parentheticals that is hard to parse. A bulleted defect list would be more scannable for the same content.

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?

There is no output schema, so the description must describe returns, and it does: per-group counts, tiny_faces_by_group, the cross_group flag with separate counts, and the 50-item cap. An agent knows what to expect back and how to control verbosity; only the overall report framing is slightly underspecified.

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% and already documents both parameters (group omission, ambiguous-name refusal, details being whole-model only). The description mostly restates this; its only real addition is the practical warning that details output 'can be very long'. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('check') and resource ('geometry problems' in groups), then enumerates the exact defect categories it detects (stray edges, open edges, non-manifold edges, duplicate edges, near-coincident vertices, tiny faces, non-planar faces, coplanar seams). This is instantly distinguishable from diagnostic siblings like measure or list_entities.

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 clear operational routing: omit 'group' for a whole-model count-only pass, pass details:true for the (very long) example items, and 'audit one group to see where its issues are'. No explicit comparison to sibling tools, but the when-to-use guidance for its own two modes is concrete.

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