Skip to content
Cranley

Measure search

Finds homes by what is measured inside them: door widths on the way to the bathroom, turning space, wall lengths, floors, steps. No listing site can search this.

What it answers

Section titled “What it answers”
  • Homes where a wheelchair can reach a bathroom through 0.81 m doors, on one floor
  • Apartments with a bedroom wall of at least 2.2 m and a 1.5 m turning circle in the bathroom

For the agent, the tool is described as: Search about two thousand Houston and Los Angeles homes by measured facts. Criteria are (measure, op, value) and must all hold; returns the matching scans ranked by how comfortably they pass, with each measured value and why it passed. Key measures: bath_route_door (narrowest door from the entrance to the best bathroom), bed_route_door_min, bath_turn, bed_wall, floors, step_free_bath, wheelchair_bath, ceiling_median, glazing_ratio.

Who it is for

Section titled “Who it is for”

Car owner checking a garage, Moving large furniture, Older adult or family, Renter checking a listing, Home robot maker, Wheelchair user looking for a home, Wheelchair user.

Inputs

Section titled “Inputs”
Input Type Required Default Notes
need string A common search, picked from a list. Asked as: “What must the home allow? wheelchair: A wheelchair reaches a bathroom from the entrance; step_free_bath: No step between the entrance and a bathroom; one_floor_living: Bedroom and bathroom on the entrance floor, no doorway steps; king_bed: A king bed fits: a bedroom wall of 3 m and 0.76 m doors to every bedroom; upright_piano: An upright piano fits: a living room wall of 3 m and a 0.85 m entrance” Saved preference search.need.
criteria array [] Every criterion must hold; added to the need’s own criteria.
city string Houston or Los Angeles.
kind string House or apartment.
sort string Rank by this measure, highest first; default by margin.
limit integer 20 Rows to return. Range: at least 1, at most 100.
near array Point to search around, (lat, lon).
within_km number Only scans this close to near.
rooms array [] Rooms the home must have, each meeting its measures (e.g. a Kitchen with area >= 12). Needs the facts database.

An input that nothing fills (the selected building, a saved preference, a persona’s preset) becomes a question to the person. The agent asks only for those.

Data used

Section titled “Data used”
Layer Id Needed If it is missing
Measures table threshold.measures required The verdict is unknown, with the reason.

What it returns

Section titled “What it returns”

A tool result: a verdict (pass, warn, fail or unknown), metrics, checks and findings, each with its source.

  • Panel blocks: VerdictHeader, MetricRow, RankedTable, EvidenceStrip, StepLog, ActionBar.
  • Its own ranked table: Margin over the criteria.
  • Speed: fast. Read-only.

How it works

Section titled “How it works”

Measure search: find homes by what is measured inside them (door widths on the way to the bathroom, turning circles, free wall lengths, floors…), over the measures table (table.py).

Reliability

Section titled “Reliability”

Every metric and finding carries its layer, its method and a high, medium or low label, set by the tool for each value. See findings and reliability.

Limits

Section titled “Limits”
  • Needs: measures table. On a scan without it, the verdict is unknown and says why.
  • A result is a planning aid, not an inspection.

On the made-up test home

Section titled “On the made-up test home”

This section was written by running the tool when the docs were built, on a hand-made RoomPlan export (no real place was scanned), with no sponsor keys and the network switched off.

Unknown The measures table has not been built yet.

Run it

Section titled “Run it”
threshold run measure_search
curl -X POST http://127.0.0.1:8787/api/tools/measure_search/run -H 'content-type: application/json' -d '{...inputs}'

Over MCP the tool is named measure_search. See MCP server and CLI.