Skip to main content
Glama
Meteor-Simulation

BULC MCP

Official
by Meteor-Simulation
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Arch import building

arch_import_building
Destructive

Creates one building story in a single undo step from drawing analysis or a spec: walls become obstacles, doors and windows become holes, with optional columns and slabs.

Instructions

Create the building on one story in ONE undo step: walls as obstacles (axis-aligned box per wall, diagonal walls stair-stepped like the 2D editor), doors as holes 'Door_n' (also evacuation exits) and windows as holes 'Win_n' at sill height (not exits), optional columns and slabs. Source: candidateId from arch_analyze_drawing (exclude walls / openings by id) or building = {walls:[{start:[x,y],end:[x,y],thickness?,height?}], doors:[{at:[x,y]|wall:n,position:0..1,width?,height?}], windows:[{at|wall,position,width?,sill?,height?}], columns:[{xb:[x1,x2,y1,y2]}|{center,size}]} in metres; wall:n counts from 1 in the order of building.walls (openings that cannot be placed are listed in warnings). story = story id (default current story; z = its zMin, wall height = its height). dryRun defaults to TRUE — report first, confirm with the user, then call again with dryRun:false. mode append (default) | replace (removes what an earlier import with the same idPrefix created).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo
storyNoStory id (draw_list_stories / project_info)
zBaseNoFloor elevation instead of the story zMin (m)
dryRunNoOnly report (default TRUE)
includeNoWhat to create: doors (true), windows (true), columns (true), floorSlab (false — slab just below the story floor), ceilingSlab (false — slab on top of the walls)
buildingNoHand-written building spec (metres) instead of candidateId. Door/window wall:n is 1-based (wall 1 = building.walls[0])
defaultsNowallHeight (default: story height), wallThickness (walls without one, default 0.2), doorWidth 0.9, doorHeight 2.1, windowWidth 1.2, windowSill 0.9, windowHeight 1.2, slabThickness 0.2 (m)
idPrefixNoId prefix (default 'A<story>_')
transformNoPlacement: origin = 'bbox_min' (default for drawings: lower-left corner of the building) | 'none' | [x,y] in drawing metres; target [x,y] (default [0,0]); rotateDeg about the target (counter-clockwise); mirrorY. Use the same origin for every story drawing of one building.
candidateIdNo
excludeWallsNoCandidate wall ids to skip
maxObstaclesNoRefuse above this many obstacles (default 3000, max 20000)
excludeOpeningsNoCandidate door/window ids to skip

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.0.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare destructive/non-idempotent/non-readonly, and the description adds substantial context beyond them: the operation is a single undo step, dryRun defaults to TRUE, mode=replace removes geometry from a prior import with the same idPrefix, and openings that cannot be placed are listed in warnings. This is exactly the extra behavioral detail an agent needs.

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?

Dense but front-loaded, leading with the outcome (create building in one undo step) before the spec details. The long inline building-spec sentence is information-heavy, though every clause maps to a real behavior.

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 13-parameter, nested-object, mutation tool with no output schema, the description covers source selection, defaults, dry-run workflow, id prefixing, and warnings. It omits transform/origin placement guidance, which lives only in the schema, but the overall coverage is strong given annotations carry the safety profile.

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 already high (85%), but the description still adds meaning: wall:n is 1-based in building.walls order, story defaults to the current story with z = zMin and wall height = story height, and mode append/replace semantics. It reinforces rather than merely restates the schema.

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 ("Create the building on one story") and enumerates exactly what is produced: walls as axis-aligned obstacles, doors/windows as named holes, columns, slabs. It clearly differentiates itself from arch_analyze_drawing, which it names as the source.

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 a clear workflow: consume candidateId from arch_analyze_drawing or supply a hand-written building spec, run dryRun (default TRUE), confirm with the user, then re-call with dryRun:false. It does not explicitly compare against the sibling arch_import_floorplan_report, so it stops short of the top score.

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