Skip to main content
Glama
joacos

archicad-tapir-mcp

by joacos

archicad_set_mesh

Modify a terrain mesh's level, skirt depth, and holes. Works on locked layers, checks the result in 3D, and supports dry runs.

Instructions

Changes a Mesh (terrain): its level, skirt depth and holes. Works on locked layers and checks the result in 3D. Revert with archicad_undo.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
guidYesThe Mesh to change.
holesNoReplaces the mesh holes with these outlines (e.g. where a path goes).
levelNoNew reference level (height of a point with z = 0).
dryRunNoOnly return what would change, without touching the model.
polygonNoReplaces the outline; z is the height of each point above the mesh level.
sublinesNoReplaces the interior level lines (survey points as 2-point lines, contours...).
skirtLevelNoNew skirt depth below the mesh surface.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds genuinely useful non-schema behavior: it operates even on locked layers, performs a 3D result check, and is reversible via archicad_undo — consistent with destructiveHint=false. It still does not say how conflicting/unspecified fields are handled.

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?

Two tight sentences with zero waste; the core effect is front-loaded and the recovery instruction follows immediately.

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 mutation tool with full schema coverage and no output schema, the definition covers what it does, its lock-layer behavior, and the revert path. It stops short of describing interaction between the geometry parameters (polygon vs holes vs sublines) or partial-update semantics, but nothing critical for invocation is missing.

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 every parameter (guid, holes, level, dryRun, polygon, sublines, skirtLevel) is already documented. The description mentions level, skirt depth and holes but adds no syntax, units, or coordinate-frame detail beyond the schema, so the baseline 3 applies.

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 (Changes) and resource (a Mesh (terrain)) and enumerates the exact aspects modified: level, skirt depth and holes. This clearly distinguishes it from siblings like archicad_create_meshes, archicad_set_slab_levels, and archicad_move_elements.

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 only implied: the description names the target object and a revert path (archicad_undo), but never says when to choose this over archicad_create_meshes or how it relates to other element-editing tools. No exclusions or preconditions are stated.

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