Deliver the User's Answer
submit_answer is one of the 32 MCP tools in Weft, the AI task manager you run by talking to Claude, Cursor, Codex or ChatGPT through one MCP endpoint. Brings back what the person said to a question the agent raised, and hands the work back with the same runId and lease, so it continues in the same attempt rather than starting a cold one. Marked as relayed, never as the person acting themselves — an answer carried by an agent and a click made by a human are different kinds of evidence, and the board keeps them apart. If the question was already answered in the Weft app, that answer is returned instead of an error: what matters is that the agent continues with the right one.
Weft is the AI task manager for solo founders and small teams.
Arguments
| Name | Type | Required | Description |
|---|---|---|---|
| questionId | uuid | yes | The questionId returned by request_input |
| answer | string | yes | What the user said, in their words (≤2000 chars) |
| value | string | no | The value of the option they picked, when they picked one |
Returns
ok, the answer that stands, and taskId/runId/leaseToken to carry on with. If the task is claimed by someone else now, a note saying so instead.
Annotations
- idempotent. Calling the tool twice with the same arguments has the same effect as calling it once.
Example
What the user says:
"10% is fine."What the AI calls under the hood:
{
"name": "submit_answer",
"arguments": {
"questionId": "…",
"answer": "10% is fine",
"value": "10"
}
}Related
- All 32 MCP tools — the catalog view.
- Shuttle — how the AI client uses these tools.
- Call this tool through your own client: see setup guides, or hit
https://letsweft.com/api/mcpdirectly.