Skip to content
Cranley

Site scorecard

Ranks candidate buildings against your requirements and weights, with a score per criterion, the deal-breakers and the evidence for each cell.

What it answers

Section titled “What it answers”
  • Find me a 40,000 to 80,000 ft² distribution warehouse in Houston under $12 a foot with 24 ft clear
  • Compare these three office buildings for a 120-person team
  • Score these retail sites for our next store

For the agent, the tool is described as: The enterprise site-selection scorecard. A business gives a profile (office, industrial, retail, flex), requirements (size range or headcount, budget per ft², docks, clear height, parking ratio, step-free entrance, highway and transit distance, flood tolerance, employee home zips) and optional weights; give 2 to 10 candidates (scans, CoStar properties, addresses, points) or none to search CoStar listings around the selected place (it is included) or in Houston or Los Angeles. Returns a ranked table, per-criterion checks with evidence and source, and deal-breakers. deep also runs industrial_fit or retail_site on each candidate.

Who it is for

Section titled “Who it is for”

Commercial property underwriter, CoStar researcher, Industrial tenant rep, Office relocation lead, Retail site selector.

Inputs

Section titled “Inputs”
Input Type Required Default Notes
profile string yes Asked as: “What kind of space is it: office, industrial (warehouse or distribution), retail or flex?” Saved preference site.profile. One of: office, industrial, retail, flex.
candidates array [] Buildings to compare (scans, CoStar properties, addresses or points); empty to find candidates.
place Place With no candidates: this building and the CoStar properties for lease around it. Filled from the selected building.
search_km number (km) 25 Search radius around place. Range: at least 1, at most 80.
city string With no candidates and no place: search this city.
max_candidates integer 5 How many candidates a search keeps. Range: at least 2, at most 10.
size_min_sf number (ft²) Smallest space that works. Saved preference site.size_min_sf.
size_max_sf number (ft²) Largest space wanted. Saved preference site.size_max_sf.
budget_sf_yr number ($/ft²/yr) Highest asking rent per ft² per year. Saved preference site.budget_sf_yr.
headcount integer People to house; sets the size range when none is given. Saved preference office.headcount.
docks_min integer Dock doors needed. Saved preference site.docks_min.
clear_height_min_ft number (ft) Clear height needed under the structure. Saved preference site.clear_height_min_ft.
parking_ratio_min number (per 1,000 ft²) Parking spaces per 1,000 ft² needed. Saved preference site.parking_ratio_min.
step_free boolean false Needs a step-free entrance (ADA). Saved preference site.step_free.
highway_max_km number (km) Furthest acceptable distance to a highway on-ramp. Saved preference site.highway_max_km.
transit_max_m number (m) Furthest acceptable walk to a bus stop or station. Saved preference site.transit_max_m.
flood string "prefer_outside" Flood risk tolerance: avoid the 1% zone outright, prefer outside it, or ignore it. Saved preference site.flood. One of: avoid, prefer_outside, any.
employees array [] Home zip codes (77002:12 for 12 people) or lon,lat points, for commutes. Saved preference commute.employees.
weights object {} Weight per criterion, 0 to 5; overrides the profile’s defaults.
must array Criteria a candidate must meet; default per profile.
deep boolean false Also run the profile’s site tool on each candidate (slow, cached).
use_osm boolean true Look up highways, transit and substations in OpenStreetMap (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
Property record costar.property required The verdict is unknown, with the reason.
Osm osm optional no distances
Rooms matterport.rooms optional record values only

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, MiniChart, CheckList, EvidenceStrip, AssumptionChips, ActionBar, StepLog.
  • Its own ranked table: Score.
  • Speed: slow. Read-only.

How it works

Section titled “How it works”

Site scorecard: rank 2 to 10 candidate buildings against a business’s requirements and weights.

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: property record. On a scan without it, the verdict is unknown and 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.

Cannot answer here Give candidate buildings, or a place or a city (Houston or Los Angeles) to search.

A phone scan has walls, doors, windows, rooms and objects, but no location, no photos and no property record.

Run it

Section titled “Run it”
threshold run site_scorecard -i place='{"scan": "<scan-id>"}'
curl -X POST http://127.0.0.1:8787/api/tools/site_scorecard/run -H 'content-type: application/json' -d '{...inputs}'

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