Skip to main content
Glama

Place furniture, doors and windows

place

Insert catalog furniture, doors, windows, lights, and beams into a floor plan by coordinates or walls, copy existing pieces, and dry-run changes before applying.

Instructions

Place catalog items, or copy= of a piece already in the project (model, finish and parts; catalog scope=project lists them). at=[x,y] is the center (doors and windows near a wall snap into it; into=[x,y] picks the swing side); wall= (+along cm) puts doors and windows in a wall, or furniture with its back to it. facing=+x|-x|+y|-y|[x,y]| turns the front toward a side, point or element, preferred to angle (clockwise degrees, y down: 0 front to +y, 90 to -x, 180 to -y, 270 to +x); a piece whose back belongs on a wall, put within 30 cm of one with neither, turns its back to it. The reply says where fronts ended: faces=f3:+y(seat), turned=f3:back to w2. Ceiling pieces hang from the ceiling the 3D draws and follow it: a pendant takes elev (shade bottom, ~150-160 over a table) or h (drop). w/d/h, pitch/roll, mat, opacity; defaults {…} fills every item; px=true reads background pixels. cat=beam with a,b=[x,y,z] makes rafters and posts. dry=true answers what it would add, the clearances and the findings, without writing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vNoPlan version (tab) to write to; switches to it first
pxNoCoordinates (`at`, `into`, `a`, `b`, `along`) are pixels of the background image
dryNoTry it without applying; see `update`. `"summary"` answers short
itemsYesThe pieces to place, one object each: `id` from the catalog (or `copy`), and where (`at`, or `wall` + `along`)
defaultsNoFields every item takes unless it sets them (cat, w, d, h, color, mat…)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
vNo
okNo
dryNo
idsNo
revNo
goneNo
textNo
addedNo
facesNo
scoreNo
turnedNo
changedNo
resolvedNo
clearancesNo
issues_newNo
propertiesNo
added_countNo
annotationsNo
score_scopeNo
new_findingsNo
changed_countNo
issues_changedNo
issues_resolvedNo
findings_changedNo
acceptance_cleanupNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed32 schema fields changedv3.0.0
    • changedInput schema / $defs / Dry / description
      Previous value: -"Runs an edit against a copy of the plan and reports what it would do. Trying a size used to mean applying it, reviewing, and undoing — a round trip that showed in the user's window and burned a revision each time. The copy has no history and is thrown away, so nothing of that happens. How much of a dry run to answer with. `true` answers with everything it would change; `\"summary\"` answers with the decision — how many pieces move, which roots, the clearances, the findings and the score — because a group that rebuilds lists ninety-seven parts for a choice that fits in five lines"New value: +"How much of a dry run to answer with: `true` everything it would change, `\"summary\"` the decision — pieces moved, roots, clearances, findings, score"
    • changedInput schema / $defs / LightSpec / properties / z / description
      Previous value: -"Source height as a fraction of the piece's height (default: its base for spots and panels, the middle otherwise)"New value: +"Source height, fraction of the piece's (default: base for spots and panels, else middle)"
    • removedInput schema / $defs / PlaceSpec / properties / cat / default
      Removed value: -""
    • addedInput schema / $defs / PlaceSpec / properties / stretch
      Added value: +{
      +  "description": "With `model`: w/d/h may stretch it unevenly; otherwise one or two of them scale it evenly",
      +  "type": "boolean"
      +}
    • addedInput schema / $defs / PlaceSpec / properties / unit
      Added value: +{
      +  "description": "With `model`: unit of its numbers, `m`, `cm`, `mm` or `in` (default: guessed from its size)",
      +  "type": "string"
      +}
    • changedInput schema / $defs / Point2 / description
      Previous value: -"[x, y] in centimeters; x grows right, y grows down"New value: +"[x, y] cm"
    • removedInput schema / properties / px / default
      Removed value: -false
    • removedOutput schema / properties / acceptance_cleanup / description
      Removed value: -"Acceptances orphaned, and the calls that clear them"
    • removedOutput schema / properties / added / description
      Removed value: -"Ids added, or their count"
    • removedOutput schema / properties / added_count / description
      Removed value: -"Roots added"
    • removedOutput schema / properties / annotations / description
      Removed value: -"Annotation switches {from, to}"
    • removedOutput schema / properties / changed / description
      Removed value: -"{id, from, to} per element changed; a count past 20"
    • removedOutput schema / properties / changed_count / description
      Removed value: -"Roots changed"
    • removedOutput schema / properties / clearances / description
      Removed value: -"Free floor around touched pieces, by id"
    • removedOutput schema / properties / dry / description
      Removed value: -"Nothing was written"
    • removedOutput schema / properties / faces / description
      Removed value: -"Where each front looks: <id>:<side>(<front>)"
    • removedOutput schema / properties / findings_changed / description
      Removed value: -"Findings changed"
    • removedOutput schema / properties / gone / description
      Removed value: -"Ids removed, or their count"
    • removedOutput schema / properties / ids / description
      Removed value: -"Ids created or touched"
    • removedOutput schema / properties / issues_changed / description
      Removed value: -"Layout issues resized"
    • removedOutput schema / properties / issues_new / description
      Removed value: -"Layout issues created"
    • removedOutput schema / properties / issues_resolved / description
      Removed value: -"Layout issues settled"
    • removedOutput schema / properties / new_findings / description
      Removed value: -"Findings created"
    • removedOutput schema / properties / ok / description
      Removed value: -"Always true"
    • removedOutput schema / properties / properties / description
      Removed value: -"Project properties changed"
    • removedOutput schema / properties / resolved / description
      Removed value: -"Findings settled"
    • removedOutput schema / properties / rev / description
      Removed value: -"Plan revision"
    • removedOutput schema / properties / score / description
      Removed value: -"Score [before, after]"
    • removedOutput schema / properties / score_scope / description
      Removed value: -"Disciplines scored"
    • removedOutput schema / properties / text / description
      Removed value: -"The reply as written"
    • removedOutput schema / properties / turned / description
      Removed value: -"Pieces turned back to a wall: <id>:back to <wall>"
    • removedOutput schema / properties / v / description
      Removed value: -"Plan version written to, when there are several"
  2. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the agent knows it writes without destroying. The description adds valuable behavioral context: `dry=true` performs a preview without writing, ceiling pieces follow the 3D ceiling, and the reply reports final facing. It does not cover undo, permissions, or rate limits.

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?

Packed into a single run-on paragraph with no line breaks or bullets. It front-loads the core purpose, but the dense stream of parameter clauses is hard to scan. Every clause adds information, but structure is poor.

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 complex tool with 5 top-level parameters and a rich schema, the description covers major modes (furniture, doors/windows, beams, ceiling fixtures, dry run) and notes the reply shape. An output schema exists, so return values needn't be fully explained. Minor edge cases like error handling are not described.

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%, so parameters are already documented. The description still adds non-schema rules: doors/windows snap into a nearby wall, `into` picks swing side, a piece within 30 cm of a wall turns its back to it, and `facing` is preferred over `angle`. These relationships go beyond 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 ('Place') and resources (catalog items, copies of existing pieces) and names the `catalog` tool for listing them. Clearly separates placement from catalog browsing. An agent can identify the tool's core action without reading the schema.

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?

Gives implied usage for placing items and special cases (doors, windows, beams, ceiling pieces), but never states when to use this versus siblings like `move`, `arrange`, or `update`. It mentions `catalog` only as a reference for listing, not as an alternative action.

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