Skip to main content
Glama

Paint a room photo

visualize_room

Paid (Muro credits, needs a Muro API key). Repaint the walls in a photo of a room, facade or roof in 1 to 12 colours at once and return one image per colour. Give the photo as image_url (a public link) or image_base64. Give each colour as brand + name_or_code from the catalogue (e.g. "Farrow & Ball" + "Hague Blue") or as hex. Without a photo it paints Muro’s sample room (or facade, roof). Every colour comes with a shopping list: the closest real paints from several brands with ΔE and a verdict; pass country to put brands sold there first. RAL works as brand "RAL" + "9005" or just "RAL 9005". Waits up to about 45 seconds; if some colours are still being painted, it returns a job_id for get_visualization. Tell the user the cost before calling: 1 credit per colour in standard quality.

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": {
      "colors": "<colors>"
    },
    "name": "visualize_room"
  }
}

Input Schema

NameRequiredDescriptionDefault
colorsYes1 to 12 colours; each one is a separate painted image
countryNoWhere the user buys paint, e.g. "PL", "DE", "US": brands sold there come first in the shopping list
matchesNoPaints to list per colour (default 5, 0 = no shopping list)
qualityNostandard ≈1K (1 credit per colour), hd ≈2K (2), ultra ≈4K (3; plan permitting)standard
surfaceNoWhat is in the photointerior
image_urlNoPublic link to the photo (JPEG, PNG or WebP, up to 12 MB). Leave out both image fields to paint Muro's sample room
image_base64NoThe photo as base64 or a data: URL, instead of image_url
match_brandsNoOnly list paints from these brands, e.g. ["Dulux", "Śnieżka"]
paint_ceilingNoInteriors only: paint the ceiling too

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say it is not read-only, not idempotent, open-world and non-destructive; the description adds substantial context beyond that — billing model and per-colour credit cost, API-key requirement, a ~45 second wait with partial results returned as a job_id, one image per colour, and an accompanying per-colour shopping list with ΔE and a verdict. These are exactly the operational facts an agent needs before committing a paid, slow call.

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?

Front-loads the most decision-relevant facts (paid, API key) and keeps every sentence informational — cost, input formats, fallback, shopping list, timeout. It is dense and somewhat run-on, with several distinct topics packed into long sentences, but there is no filler to remove.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With nine parameters and no output schema, the description carries the return-shape burden and does so: one image per colour, a shopping list with ΔE and verdicts, and a job_id fallback for unfinished colours. Billing, latency, prerequisites, and input alternatives are all covered, leaving nothing an agent needs missing.

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 structured fields already carry the basics, but the description adds genuine meaning: colour can be given as brand + name_or_code from the catalogue or as hex, RAL works either as brand 'RAL' + '9005' or as 'RAL 9005', and country reorders brands actually sold there. The quality/cost mapping is covered in both places, so the marginal gain is real but not exhaustive.

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 ('Repaint the walls in a photo of a room, facade or roof') plus the output contract ('one image per colour') and the input cardinality (1 to 12 colours). This is far more than a restatement of the name 'visualize_room' and makes the tool's function unambiguous.

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 invocation conditions: it is paid and needs a Muro API key, and the agent must tell the user the cost (1 credit per colour in standard quality) before calling. It also offers the no-photo fallback (Muro's sample room/facade/roof) and the continuation path via get_visualization when a job_id is returned. It does not explicitly rule out adjacent tasks like a lighting change, but the repaint scope is stated concretely.

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