collect_answer
Capture the candidate's spoken answer after asking a question, auto-grade math responses, and return rubric components for framework answers to score.
Instructions
Listen for the candidate's spoken answer, then grade what can be graded.
Call it right after asking a question. If it returns ready: false, they're
still thinking — call it again. Don't fill the silence; interviewers let
candidates work.
Math answers come back fully graded (deterministic, instant). Framework and
synthesis answers come back with the rubric's component labels and the
committed transcript — read them, decide which components the candidate
actually covered, and pass those ids to score.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "collect_answer"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| max_wait | No | Seconds to wait this call. | |
| acknowledge | No | A short line spoken the instant their answer lands — 'Got it, let me think about that.' Removes the dead air while you reason. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||