Skip to main content
Glama

Furnish rooms in the model

vedutum_furnish_rooms
Destructive

Places furniture in the rooms of a project’s model the way a planner would: by room type (living, kitchen, bedroom, bath, office, meeting…), clear of doors and windows, with 90 cm passages. One room by name or every room of a storey or of the house; "add" fills only empty rooms, "replace" furnishes anew. Changes the model; vedutum_undo_last_change takes it back. Costs no points.

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": {
      "project_id": "<project_id>"
    },
    "name": "vedutum_furnish_rooms"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo"add" (default) leaves furnished rooms as they are; "replace" removes their furniture first
roomNoOnly this room, by its name on the plan, e.g. "Wohnen" or "Kind 1"
storeyNoOnly this storey (0 = ground floor); default every read storey
languageNoLanguage of the answer: "de" (German) or "en" (English). Default "de".
terracesNoAlso set out the ground floor terraces (default true when furnishing a whole storey)
project_idYesProject id, as vedutum_list_projects returns it

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and non-idempotent, so the description's job is to add context, which it does: it states the model is changed, names the undo path, and notes the operation costs no points. The destructive behaviour of 'replace' is disclosed, though the description doesn't say what happens to partially furnished rooms or whether placements are stable across repeated runs (relevant given idempotentHint=false).

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, front-loaded and free of padding; the domain framing is done in one clause and the behavioural facts (undo, cost) are packed into two short sentences. Minor cost from the slightly conversational 'the way a planner would' phrasing, but nothing that displaces the essential information.

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 six-parameter mutation tool with no output schema, the description covers scope, modes, side effects, undo, and cost, which is most of what an agent needs before calling it. A note on what the model looks like afterwards, or on failure when a room name doesn't match, would complete it.

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 baseline is 3; the description still adds value by framing how room and storey interact as a scope selector ('one room by name or every room of a storey or of the house') and by restating the add/replace contract. It goes modestly beyond the per-field text without adding new syntax details.

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?

A specific verb ('places furniture') on a specific resource ('rooms of a project's model'), with the operating rules (by room type, clear of doors/windows, 90 cm passages) stated immediately. It is unmistakable against siblings like vedutum_set_design or vedutum_model_geometry.

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

Usage Guidelines5/5

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

It defines the selection scope explicitly (one named room, one storey, or the whole house) and the two modes with their conditions: 'add' fills only empty rooms, 'replace' furnishes anew. It also names the correct follow-up tool, vedutum_undo_last_change, for taking it back.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources