Skip to main content
Glama

See a stone on your kitchen

visualize_kitchen

Render a slab from the Austin yard onto a photo of the user's own kitchen or bath, and return the image with a price estimate. Pass a public image URL of the room (JPEG/PNG/WebP) and a stone slug from search_stones. The picture usually comes back in this reply (about 15-40 seconds); if it is not ready in time, call get_visualization with the returned id. Optional cabinet_wood / hardware_finish (from list_finishes) preview a different cabinet finish or hardware; visualization only, we don't sell cabinets or hardware.

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": {
      "room_image_url": "<room_image_url>",
      "stone_slug": "<stone_slug>"
    },
    "name": "visualize_kitchen"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqftNoCountertop square feet, for the price estimate
stone_slugYesStone slug from search_stones, e.g. '2cm-taj-mahal-premium-leather'
cabinet_woodNoVisualization only (we don't sell cabinets). One of: keep, white-oak, red-oak, walnut, cherry, maple, hickory, painted-white, painted-navy, painted-greige, painted-sage. Default keep.
room_image_urlYesPublic URL of a photo of the room, countertops visible
hardware_finishNoVisualization only (we don't sell hardware). One of: keep, matte-black, brushed-nickel, brushed-brass, polished-chrome, oil-rubbed-bronze, unlacquered-brass. Default keep.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / cabinet_wood
      Added value: +{
      +  "description": "Visualization only (we don't sell cabinets). One of: keep, white-oak, red-oak, walnut, cherry, maple, hickory, painted-white, painted-navy, painted-greige, painted-sage. Default keep.",
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • addedInput schema / properties / hardware_finish
      Added value: +{
      +  "description": "Visualization only (we don't sell hardware). One of: keep, matte-black, brushed-nickel, brushed-brass, polished-chrome, oil-rubbed-bronze, unlacquered-brass. Default keep.",
      +  "maxLength": 40,
      +  "type": "string"
      +}
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses latency (15-40 seconds), the partial-result path with a returned id and follow-up call, the requirement for an externally hosted public image (consistent with openWorldHint), and what the response contains. The cabinet/hardware disclaimer also sets expectations that those parameters are cosmetic only.

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?

Four sentences, each carrying distinct load: action, required inputs and their source, timing plus fallback, and optional finish preview with a scope disclaimer. The core 'what it does' is front-loaded and nothing is redundant.

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 no output schema, the description covers return values, timing, and the failure/retry path, which is exactly what an agent needs before calling. For a five-parameter tool with full schema coverage, there is no material gap left.

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 the baseline is 3; the description still adds value by specifying accepted image formats (JPEG/PNG/WebP) and that the URL must be public, which the schema's bare 'format: uri' does not convey. It does not mention sqft, but that parameter is self-describing in 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 — rendering a slab onto a photo of the user's kitchen or bath — plus what it returns (image with price estimate). Scope details (Austin yard, kitchen/bath) and the named sibling sources (search_stones, get_visualization, list_finishes) make it distinguishable from adjacent tools at a glance.

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?

Clearly states the inputs required (public room image URL, stone slug from search_stones) and routes the agent to get_visualization when the async result isn't ready. It does not distinguish when to visualize versus when to go straight to estimate_job/get_pricing, so the alternative-selection guidance is strong but not exhaustive.

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