agent_feedback
agent_feedbackRate a prior Mako tool run by selecting a grade (full, partial, no) and reason codes. Use only for notably good, bad, or wrong results.
Instructions
Append-only feedback tool for rating a prior Mako tool run from the agent perspective. Use sparingly when a result was notably good, notably bad, or wrong; do not emit routine feedback after every call. Requires referencedToolName and referencedRequestId so each row is tied to a specific prior run. Grade semantics: full = helped complete the task, partial = somewhat useful but flawed, no = wrong or wasted the turn. Starter reason codes: full: answer_complete, evidence_sufficient, trust_matches; partial: partial_coverage, noisy, stale_evidence, missing_known_caller, top_not_useful; no: answer_wrong, wasted_turn, tool_did_nothing, schema_missing.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"referencedToolName": "<referencedToolName>",
"referencedRequestId": "<referencedRequestId>",
"grade": "<grade>",
"reasonCodes": "<reasonCodes>"
},
"name": "agent_feedback"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| grade | Yes | ||
| reason | No | ||
| projectId | No | ||
| projectRef | No | ||
| reasonCodes | Yes | ||
| referencedToolName | Yes | ||
| referencedRequestId | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| _hints | Yes | ||
| eventId | Yes | ||
| toolName | Yes | ||
| projectId | Yes | ||
| capturedAt | Yes |