Office fit

Whether your team fits this suite as built: desks, private offices, meeting rooms and kitchen, with the listed size and the last tenant beside it.

What it answers

• Will 28 people with 6 private offices and two meeting rooms fit here?
• How many desks does this suite hold?

For the agent, the tool is described as: Test a tenant program (headcount, private offices, meeting rooms and seats, kitchen) against one office scan. Counts what the suite has from room labels and measured areas, shows which room serves as what, compares listed against measured area (load factor), the last tenant’s employee count against computed capacity, and the asking rent. Returns pass/warn/fail and up to three changes that would make it fit. Labels unlabelled rooms first (slow once).

Who it is for

CoStar researcher, Office relocation lead, Office tenant, Remote worker, Plant lover or home office worker choosing a room.

Inputs

Input	Type	Required	Default	Notes
scan	string	yes		Scan id. Filled from the selected building.
headcount	integer	yes		Asked as: “How many people need a seat?” Saved preference office.headcount. Range: at least 1, at most 2000.
private_offices	integer		0	Asked as: “How many of them need a private office?” Saved preference office.private_offices. Range: at least 0.
meeting_rooms	integer		1	Asked as: “How many meeting rooms do you need?” Saved preference office.meeting_rooms. Range: at least 0.
meeting_seats	integer		6	Asked as: “How many seats should the largest meeting room have?” Saved preference office.meeting_seats. Range: at least 2.
kitchen	boolean		true	Needs a kitchen or break room. Saved preference office.kitchen.
desk_m2	number (m2)		6.5	Open-plan area per workstation, aisles included. Saved preference office.desk_m2. Range: at least 3.5, at most 15.
seat_m2	number (m2)		2.3	Meeting room area per seat. Saved preference office.meeting_seat_m2. Range: at least 1.4, at most 5.
office_min_m2	number (m2)		7.5	Smallest room that works as a private office. Saved preference office.private_office_min_m2. Range: at least 4, at most 20.
label_with_vision	boolean		true	Label unlabelled rooms from the panoramas first (slow once).

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

Layer	Id	Needed	If it is missing
Rooms	matterport.rooms	required	The verdict is unknown, with the reason.
360° photos	matterport.panos	optional	existing labels
Property record	costar.property	optional	no record comparison

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: a colour per room; pins on what it found; doors, walls or rooms coloured by status.
• Panel blocks: VerdictHeader, MetricRow, CheckList, MiniChart, FloorPlanMini, AssumptionChips, Controls, EvidenceStrip, StepLog.
• Speed: slow. Read-only.

How it works

Office fit: does a team’s program fit this suite as built? Rooms come from the label overlay (room_labeller), areas from the scan, the comparison from the CoStar record (listed space, last tenant, asking rent).

Reliability

Sources this tool gave on the test cafe:

Where it came from	Layer	Method	Reliability	Note
Simulated from the scan	matterport	simulation	medium	Capacity from measured areas and your space standards
Measured from the scan	matterport	geometry	high	Room floor areas from the scan
Seen in a model	model	vision	medium	Room types from the room labeller

The tool sets the label for each value. A model never does. The tools give a scan’s wall graph the layer matterport whichever device made the scan, so a phone scan’s geometry carries that label too.

Limits

• Needs: rooms. 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 cafe

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: headcount = 6 (an answer given for this example).

Fail Your team does not fit: 0 desks for 6 people, 0 private offices, 0 meeting rooms for the 1 you need.

Value	Result	Where it came from	Reliability
People seated as built	0	Simulated from the scan	medium
People to seat	6	Simulated from the scan	medium
Measured area inside the suite	84 m²	Measured from the scan	high
Area your program needs	74.5 m²	Simulated from the scan	medium
Desks in open areas and spare offices	0	Seen in a model	medium
Private offices	0	Seen in a model	medium
Meeting rooms	0	Seen in a model	medium
Kitchens	1	Seen in a model	medium
Restrooms in the suite	1	Seen in a model	medium
Reception	0	Seen in a model	medium

1 more values are in the full result.

Check	Measured	Against	Status
Desks for everyone without a private office	0	6 desks	fail
Private offices	0	0 rooms	pass
Meeting rooms	0	1 rooms	fail
Seats in the largest meeting room	0	6 seats	warn
Kitchen or break room	1	1 rooms	pass

Findings: 1 fail, 1 warn.

What it reported while it ran:

1. Read 4 rooms and their labels
2. Allocated rooms: 0 desks, 0 private offices, 0 meeting rooms

Run it

threshold run office_fit --scan <scan-id>
curl -X POST http://127.0.0.1:8787/api/tools/office_fit/run -H 'content-type: application/json' -d '{...inputs}'

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