Snuug room calculators

Sofa fit calculator

sofa_fit

Read-onlyIdempotent

Use when someone asks whether a sofa (or another large piece) will fit through a door, round a turn in a hall or up to a room. Applies the furniture shops’ straight, tipped-back, on-end and swing tests and grades each ok, tight or no.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "sofa_fit"
  }
}

Input Schema

Name	Required	Description	Default
`route`	No	turn if the sofa must turn into the room after the door, straight if it goes straight on.	turn
`door_width_cm`	No	The door’s clear width: the gap with the door open, frame to door edge (cm).
`hall_width_cm`	No	The width of the hall or landing beyond the door, where the sofa must turn (cm).
`sofa_depth_cm`	No	The sofa’s depth, back to front (cm).
`sofa_width_cm`	No	The sofa’s width, arm to arm (its length when carried) (cm).
`door_height_cm`	No	The door’s clear height (cm).
`sofa_height_cm`	No	The sofa’s height, floor to the top of the back (cm).
`sofa_diagonal_cm`	No	The sofa’s diagonal depth: from the back bottom corner to a straight edge laid from the top of the back to the front of the arm (cm).

Output Schema

Name	Required	Description
`tool`	Yes	The tool, as named in its API and page URLs.
`notes`	Yes	Caveats to pass on with the answer.
`snuug`	Yes	One line about Snuug, the app behind the calculators.
`answer`	Yes	The answer as named values.
`inputs`	Yes	Every input as the tool used it: given, a default, or filled in from the rules.
`sources`	Yes	The sources of the rules used. Every rule cites its source, with the date it was checked.
`summary`	Yes	The answer in one sentence to quote.
`version`	Yes	The version of this contract.
`working`	Yes	How the answer was worked out, one step a line.
`page_url`	Yes	The calculator on snuug.app with these inputs filled in.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds genuine behavioral substance: it names the four physical tests applied (straight, tipped-back, on-end, swing) and the grading scale (ok, tight, no), which tells the agent what kind of answer to expect and how to interpret a marginal result. It does not discuss assumptions such as clear-width measurement or rounding, which keeps it from a 5.

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?

Two sentences, zero padding, and front-loaded with the trigger condition before the method. Every clause earns its place: the first routes the agent, the second explains what the tool actually computes and returns.

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?

An output schema exists, so return values need no explanation, and all eight parameters are fully documented in the schema with ranges and defaults. The description supplies the remaining context an agent needs — the tests being applied and the grade vocabulary — making the definition complete for a read-only calculator of this complexity.

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?

Schema description coverage is 100% and every parameter carries a unit, range and plain-language definition, so the schema already does the semantic work. The description adds only an indirect hint at the route enum via 'round a turn' and 'straight', and says nothing about defaults or that all eight inputs are optional. Baseline 3 applies when the schema is this rich.

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 concrete verb-and-resource: it evaluates whether a sofa (or other large piece) fits through a door, round a hall turn, or up to a room, and returns per-test grades of ok/tight/no. That is specific enough that an agent can distinguish it from sizing calculators like curtain_size or rug_size purely on the domain described.

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?

'Use when someone asks whether a sofa ... will fit through a door, round a turn in a hall or up to a room' gives an explicit triggering condition with three concrete scenarios. There are no when-not cases or named alternatives, but the sibling calculators are non-overlapping so no routing ambiguity is left open.

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

All Snuug room calculators tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?