Skip to main content
Glama

Itemized countertop quote (+ optional kitchen render)

generate_quote

Build an itemized countertop quote at ATX Granite King's posted rates (install $38/sq ft, $30/sq ft over 1,000 sq ft, Budget Collection slabs $999) from the user's sq ft or counter runs, island and options. Items with no posted price are listed as quoted at measure. Returns at once with a shareable quote page URL. If room_image_url (a public photo of the user's kitchen) is given, the stone is also rendered onto it (optionally with a cabinet_wood / hardware_finish from list_finishes) and the picture usually comes back in this reply. No public photo link? Give the user the quote_url: they can upload a kitchen photo there.

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": {
      "stone_slug": "<stone_slug>"
    },
    "name": "generate_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity of the job (same price within 60 miles of Austin)
edgeNoEdge profile; eased is standard, others quoted at measure
nameNoOptional name to show on the quote
runsNoCounter runs (up to 12): length_in, optional depth_in (default 25.5), optional label
sqftNoCountertop square feet, if known. Otherwise give runs (and island).
notesNo
sinksNoSink cutouts, default 1 (included in install)
islandNoIsland top in inches
tear_outNoTear-out of old tops (quoted at measure)
stone_slugYesStone slug from search_stones, e.g. '2cm-taj-mahal-premium-leather' or 'budget-absolute-white'
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.
cooktop_cutoutNoCooktop / extra cutout (quoted at measure)
room_image_urlNoPublic URL of a photo of the kitchen, 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.
backsplash_height_inNoStone backsplash height in inches along the runs; 0 = none (default). Quoted at measure.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

The description adds real behavior beyond the annotations: unpriced items are 'quoted at measure,' the call returns at once with a shareable URL, and the render 'usually comes back in this reply' rather than being guaranteed. That non-determinism and the fallback upload path are exactly the kind of context annotations cannot carry. It does not explain side effects such as whether each call creates a new quote page, which matters 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?

Purpose is front-loaded, then pricing, then return behavior, then the image fallback — a sensible order with no filler. The second sentence is long and packs several distinct facts, but every clause carries information an agent needs.

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 15-parameter tool with nested objects and no output schema, the description covers pricing rules, the return artifact, optional rendering, and the realistic case where rendering does not come back. The main gap is what the itemized quote actually contains and whether repeated calls spawn duplicate quote pages.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 93% schema description coverage, the schema already documents nearly every parameter, so the baseline is 3. The description contributes the choice between sqft and runs-plus-island and notes that options without posted prices are deferred to measure, but it adds no format or unit detail beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource: 'Build an itemized countertop quote at ATX Granite King's posted rates,' with concrete pricing rules and the immediate return value (a shareable quote page URL). An agent can tell this produces a quote artifact with optional rendering. It does not explicitly distinguish itself from siblings like get_quote, request_quote, or estimate_job, so it stops short of a 5.

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 operational routing: derive stone_slug from search_stones, take cabinet_wood/hardware_finish from list_finishes, and supply either sqft or runs plus island. It also handles the common failure path explicitly — if there is no public photo link, hand the user the quote_url to upload there. No explicit when-not-to-use-this-tool guidance versus the quote-related siblings.

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