What it does
Cost vs value of delegated work over a window of days, per agent (task_runs.agent_name; null = unnamed) and per project: runs, tool calls, minutes and reported tokens spent; spend against budget on the tasks that have a cap (budget_tool_calls / budget_minutes — null when nothing here is capped); tasks a human approved vs sent back and the rejection rate; the value (Task.value) and impact (1–5) of the approved ones; and tool calls and minutes per approved task. Units only — there is no currency figure, because Done stores none. A decision counts only when the task also had a run in the window, credited to that task's most recent run. Narrowed to the token's project or workspace when the token is scoped. Reports only: nothing is written.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
days | integer | Optional | How far back to look, by run start and decision time (default 30; the app offers 7, 30 and 90).
|
Annotations
The hints the server sends with this tool. A host reads them to decide whether to ask you before a call.
- Read-only
readOnlyHint: true - Changes nothing.
- Destructive
destructiveHint: false - Only adds or reads; nothing already there is removed or overwritten.
- Idempotent
idempotentHint: — - Doesn't apply: the tool changes nothing.
- Open world
openWorldHint: false - Touches only your own Done account.
Which tokens can call it
A connection made with OAuth has full access. A token from Settings → Agent access → Extra MCP tokens can be narrowed, and a narrowed token never sees beyond its project or workspace.
- Full accessAllowed
- Read-only tokenAllowed
- Single-project tokenAllowed
- Single-workspace tokenAllowed
Try it
With Done connected, ask your assistant something like:
“Compare what my agents cost with what they delivered this month.”
Connect Done to your assistant
One MCP endpoint per account, over OAuth or a token. Step-by-step setup for each client: