Retail site
Parking counted from the air and its ratio, the road the site faces, anchors and neighbouring shops, and walk-in proxies.
What it answers
Section titled “What it answers”- Is this a good spot for our next store?
- How much parking does this retail site have per 1,000 ft²?
For the agent, the tool is described as: For a shop or restaurant site (scan, CoStar property or point): parking stalls counted on the aerial (parking_count) and stalls per 1,000 ft² of the store; the main road it faces (class, lanes, setback); anchor stores within 1.5 km and shops, food and services within a walk radius (co-tenancy); bus stops and mapped homes and offices nearby as walk-in proxies. OpenStreetMap based.
Who it is for
Section titled “Who it is for”Commercial property underwriter, Retail site selector.
Inputs
Section titled “Inputs”| Input | Type | Required | Default | Notes |
|---|---|---|---|---|
place |
Place | yes | The site: a scan, a CoStar property, an address or a point. Filled from the selected building. | |
store_sf |
number (ft²) | Store size, for the parking ratio; default the building’s rentable area. Saved preference retail.store_sf. |
||
parking_ratio_min |
number (per 1,000 ft²) | 4.0 |
Stalls per 1,000 ft² the store needs. Saved preference site.parking_ratio_min. Range: at least 0, at most 20. |
|
radius_m |
integer (m) | 400 |
Walk radius for neighbours. Saved preference retail.radius_m. Range: at least 100, at most 1500. |
|
count_parking |
boolean | true |
Count stalls on the aerial with parking_count (slow, cached). |
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 |
|---|---|---|---|
| Osm | osm |
required | The verdict is unknown, with the reason. |
| Aerial photo | vexcel.ortho |
optional | no stall count |
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,CheckList,EvidenceStrip,AssumptionChips,StepLog. - Speed: slow. Read-only.
How it works
Section titled “How it works”Retail site: what a chain looks at before it signs for a shop.
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: osm. On a scan without it, the verdict is
unknownand says why. - It is slow: progress steps reach the workspace while it runs.
- 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.
Inputs used: parking_ratio_min = 4 (preset of the persona “Retail site selector”).
Unknown This place has no location.
Run it
Section titled “Run it”threshold run retail_site -i place='{"scan": "<scan-id>"}'curl -X POST http://127.0.0.1:8787/api/tools/retail_site/run -H 'content-type: application/json' -d '{...inputs}'Over MCP the tool is named retail_site. See MCP server and CLI.