Skip to main content
Glama

Will the sofa fit?

check_sofa_fits
Read-onlyIdempotent

Checks whether a sofa (or each of its delivery boxes) goes through a door, turns from a corridor into the door, fits in a lift (cabin and door), goes up stairs (with or without a landing turn) and how much walking space it leaves in the room (60 cm minimum, 90 cm comfortable). Returns si/justo/no for each step, how it passes (straight, on end, tilted using the diagonal depth), advice and the method. With a catalogue product_id it uses that product's measurements and package sizes.

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": "check_sofa_fits"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage of the answer (default: es). Content is in Spanish; translate it if needed.
room_wallNoLength of the wall where the sofa goes in cm.
door_widthNoDoor opening width in cm.
lift_depthNoLift cabin depth in cm.
lift_widthNoLift cabin width in cm.
product_idNoOptional catalogue id (from find_sofas); when present, its measurements and packages are used.
room_depthNoDistance from that wall to the opposite wall or furniture in cm.
sofa_depthNoSofa depth in cm.
sofa_widthNoSofa width (arm to arm) in cm.
door_heightNoDoor opening height in cm.
lift_heightNoLift cabin height in cm.
sofa_heightNoSofa height in cm.
stairs_turnNoThe stairs turn at a landing.
chaise_depthNoOptional depth of the chaise longue (for the room check) in cm.
stairs_widthNoStairs clear width in cm.
use_packagesNoIf the product comes in boxes, check the boxes (default true).
corridor_widthNoCorridor width before the door in cm.
lift_door_widthNoLift door width in cm.
stairs_headroomNoStairs headroom in cm.
lift_door_heightNoLift door height in cm.
sofa_diagonal_depthNoOptional diagonal depth of the sofa in cm.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real substance on top: the si/justo/no verdict vocabulary, the physical methods used (straight, on end, tilted via diagonal depth), the 60 cm minimum versus 90 cm comfortable room thresholds, and that advice plus method are returned. The notable omission is behavior when little or no geometry is supplied — with zero required parameters, an agent gets no guidance on the minimum viable input.

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?

A single long opening sentence front-loads the checks, followed by the return values and the product_id shortcut, so nothing is buried. It is dense but every clause carries distinct information; the only cost is a lengthy run-on that is slightly harder to scan than a short bulleted list.

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 21-parameter tool with no output schema, the description does the important work: it explains the verdict format and what supplementary output comes back. The remaining gap is input completeness — which subset of measurements is needed for each check (door only, lift only, stairs only) is left for the agent to infer.

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%, so all 21 parameters (door_width, lift_door_height, stairs_headroom, use_packages, etc.) are already documented in the schema. The description adds meaning only at the margins — the 60/90 cm room thresholds and the fact that product_id overrides manual dimensions — while largely restating what the schema says. Baseline 3 is the right level here.

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?

The description names a specific verb plus a precisely enumerated scope: door passage (including per delivery box), corridor-to-door turn, lift cabin and door, stairs with or without a landing turn, and residual room space. That is far more than the title implies, and it distinguishes the tool from siblings like sofa_guide and sofa_bed_advice, which are not measurement checks.

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?

It clearly establishes the situation the tool is for and ties itself to the catalogue flow by noting that a product_id from find_sofas supplies measurements and package sizes. It does not state when not to use it or what to do when no catalogue product matches, so it lacks explicit exclusions or named alternatives.

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