post_prompt_suggestion
Propose a revised system prompt that addresses test case failures. It explains failing cases, the change made, and expected improvement for user review.
Instructions
Queue a revised system prompt for the user to review.
Always explain in reasoning:
which test cases were failing and why
what specific change you made to the prompt
why you expect this change to fix those cases
In gated mode (start_optimization_session): user reviews in UI, then approves or rejects. In loop mode (loop_optimization, loop_regression): call apply_suggestion immediately after.
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": {
"workspaceId": "<workspaceId>",
"prompt": "<prompt>",
"reasoning": "<reasoning>"
},
"name": "post_prompt_suggestion"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| workspaceId | Yes | ||
| prompt | Yes | The full revised system prompt | |
| reasoning | Yes | What changed and why | |
| expectedGain | No | e.g. "fixes failing classify queries by adding format instructions" |