Commute fit
Estimated drive time from where your people live to each candidate office: the median, who gets a long commute, and transit nearby.
What it answers
Section titled “What it answers”- Our people live in these zip codes; which office keeps commutes short?
For the agent, the tool is described as: For an office relocation: given employees’ home zip codes (or points) and 1 to 10 candidate buildings, estimates each person’s one-way drive (straight line x detour, a low-reliability estimate), the head-weighted median per candidate, who would commute longer than a limit or lose time against the current office, and bus and rail stops near each candidate.
Who it is for
Section titled “Who it is for”Office relocation lead, Office tenant.
Inputs
Section titled “Inputs”| Input | Type | Required | Default | Notes |
|---|---|---|---|---|
candidates |
array | yes | Candidate offices: scans, CoStar properties, addresses or points. Asked as: “Which buildings are you choosing between?” | |
employees |
array | yes | Asked as: “Where do your employees live? Zip codes, with a head count after a colon (77002:12), or lon,lat points.” Saved preference commute.employees. |
|
current |
Place | Where the office is now, to show who gains or loses time. | ||
long_min |
number (min) | 45 |
A one-way commute longer than this counts as long. Saved preference commute.long_min. Range: at least 10, at most 180. |
|
worse_min |
number (min) | 15 |
A move that adds this much to someone’s commute is flagged. Saved preference commute.worse_min. Range: at least 1, at most 120. |
|
detour |
number | 1.3 |
Road distance over straight-line distance. Saved preference commute.detour. Range: at least 1.0, at most 2.5. |
|
check_transit |
boolean | true |
Count bus stops and rail stations near each candidate (OpenStreetMap). |
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 |
optional | no transit 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,RankedTable,MiniChart,CheckList,EvidenceStrip,StepLog. - Its own ranked table: Median min, Long commutes %, Longest min, Transit stops 800 m.
- Speed: fast. Read-only.
How it works
Section titled “How it works”Commute fit: how long employees would drive to each candidate office, from where they live (zip codes or points).
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”- 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.
Not run: it needs candidates, employees, which only a person or a phone on site can give.
Run it
Section titled “Run it”threshold run commute_fitcurl -X POST http://127.0.0.1:8787/api/tools/commute_fit/run -H 'content-type: application/json' -d '{...inputs}'Over MCP the tool is named commute_fit. See MCP server and CLI.