Skip to main content
Glama

Evolution Manage Tool

evolution_manage
Destructive

Review, 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

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: list, analyze, approve, apply, reject
deadline_msNoOptional: 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_idYesFilter by agent ID (required)
statusNoFilter by status: pending, approved, applied, rejected
limitNoMax results (default 10, max 50)
proposal_idYesThe evolution proposal UUID to approve
reasonNoOptional reason for rejection
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explicitly warns that apply is destructive and irreversible without manual rollback, going beyond the destructiveHint annotation. It also describes read vs. write actions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, well-structured with bullet points for actions, and front-loads the purpose. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the workflow, actions, and rollback details. No output schema exists, but it mentions what analyze returns. Sufficient for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with descriptions for all parameters. The description adds context for the action parameter's values, but the schema already handles semantics well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it manages AI-generated improvement proposals and lists specific actions (list, analyze, approve, apply, reject). It differentiates from siblings by its focus on evolution proposals.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use each action (e.g., analyze returns rationale, apply is destructive) and mentions rollback via another tool. It lacks explicit comparisons to alternatives but provides sufficient context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/escapeboy/agent-fleet-o'

If you have feedback or need assistance with the MCP directory API, please join our Discord server