Evolution Manage Tool
evolution_manageReview, approve, apply, or reject AI-generated improvement proposals for agents. Proposals suggest prompt tweaks, model swaps, or skill additions based on recent run analysis.
Instructions
AI-generated improvement proposals — the platform analyzes recent agent runs and suggests prompt tweaks, model swaps, skill additions. Proposals must be reviewed (analyze), then either apply (mutates the target agent/skill) or reject. apply is irreversible without a manual rollback through agent_advanced.rollback.
Actions:
list (read) — optional: status (pending/applied/rejected), target_type, limit.
analyze (read) — proposal_id. Returns LLM-generated rationale, confidence score, diff preview.
approve (write) — proposal_id. Marks as approved without applying (queue for batch apply).
apply (DESTRUCTIVE) — proposal_id. Mutates the target entity in place; rollback only via config_history snapshot.
reject (write) — proposal_id, reason. Closes the proposal.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Action to perform: list, analyze, approve, apply, reject | |
| deadline_ms | No | Optional: max wall-clock time (ms) the tool may spend. If exceeded during the call, returns a DEADLINE_EXCEEDED error. Minimum 100 ms. Leave unset for no deadline. | |
| agent_id | Yes | Filter by agent ID (required) | |
| status | No | Filter by status: pending, approved, applied, rejected | |
| limit | No | Max results (default 10, max 50) | |
| proposal_id | Yes | The evolution proposal UUID to approve | |
| reason | No | Optional reason for rejection |