What it does
Gather everything a human approving this task would want to check, in one call: acceptance-criteria progress, what the runs actually spent against the task's budget, every receipt the runs left behind, the deliverables produced, links to the run traces, and edits — every field rewritten on this task, by an agent or a human, newest first. agent_edits_since_human counts the agent edits made since a human last touched it: read it before you trust the criteria, because criteria that were rewritten after the work started are not the bar anyone agreed to. unverified is true when nothing checkable was left at all — no receipt, no deliverable, no trace. Use before approve_task or reject_task, and before propose_completion to see whether your own claim is checkable yet. Reports only: it computes no score and changes nothing.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
id | string | Required | Task id |
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 tokenRefused
- Single-workspace tokenAllowed
Try it
With Done connected, ask your assistant something like:
“Show me the evidence behind the API task before I approve it.”
Connect Done to your assistant
One MCP endpoint per account, over OAuth or a token. Step-by-step setup for each client: