Field check
Lists what the scan could not settle and a person on site can, and records what they found: confirmed, contradicted or measured.
What it answers
Section titled “What it answers”- What should I check when I visit?
- What did the visit change?
For the agent, the tool is described as: The on-site checks a scan’s results call for (clear door widths, steps, smoke alarms not seen, the floor height for flood, window facing) and the outcome of each one a person has done with the phone app: confirmed, contradicted or measured, with the capture as evidence. Run from the phone link; by hand it only explains how to start.
Who it is for
Section titled “Who it is for”Apartment manager, Fire captain, Houston homeowner before a storm, Los Angeles household preparing for an earthquake, Older adult or family, Wheelchair user.
Inputs
Section titled “Inputs”| Input | Type | Required | Default | Notes |
|---|---|---|---|---|
scan |
string | yes | Scan id. Filled from the selected building. | |
tasks |
array | The scan’s phone tasks with their outcomes, from the capture routes. Missing when run by hand: then it explains how to start. | ||
offer_phone |
boolean | false |
Set by the server: no phone has sent anything to this workspace yet, so the verdict says how to start one. Never set on the phone. |
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 |
|---|---|---|---|
| Capture | phone.capture |
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.
- Draws on the building: pins on what it found.
- Panel blocks:
VerdictHeader,MetricRow,CheckList,EvidenceStrip,FloorPlanMini,StepLog. - Speed: fast. Read-only.
How it works
Section titled “How it works”Field check: the on-site list. Other tools end in “measure on site”, “too close to call” and “not seen”; this turns those into things to do with a phone in the building, and when a capture comes back it reports what the site says about the scan’s result: confirmed, contradicted, or measured for the first time.
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: phone.capture. On a scan without it, the verdict is
unknownand 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 Open this workspace on a phone (Continue on phone) to get the on-site checks for this building. They come from the other tools' results, so run those first.
Run it
Section titled “Run it”threshold run field_check --scan <scan-id>curl -X POST http://127.0.0.1:8787/api/tools/field_check/run -H 'content-type: application/json' -d '{...inputs}'Over MCP the tool is named field_check. See MCP server and CLI.