Skip to main content
Glama

run_campaign

Executes a full self-improving campaign: mines past sessions, improves workflows, validates each output through multiple checks, and promotes only verified improvements.

Instructions

AUTONOMOUS SUPERVISOR (opt-in: SUPER_LOOP_ALLOW_EXEC=1). One call drives the whole campaign itself — intake → work the target queue (mine → improve) → for each improve target: hash-lock baseline → freeze benchmark → measure the bar on a real worker → FullTestBatches (3-5 frontier workers, each output VALIDATED through the enforcement boundary) → supervisor delta → reverify → promote (bank a Stone) → advance/retire → re-mine — and keeps going until the operator stop-file. Worker output is never trusted: summary-only / early-stop / fake-metric / self-promote / phase-skip / copied-public are rejected and re-entered, and invalid batches do not count toward retirement. maxBatches bounds the in-call MCP run (a safety cap, NOT completion); the standalone super-loop-run CLI runs it until the stop-file. Returns the exact string MISSING_FULL_PRIVATE_LOOPS if a full private loop is absent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
runIdYes
configYes{ task, routes:[3-5 frontier], benchmark:{name,taskValueDimensions,resourceDimensions,cases,oracle}, targets:[{kind:"mine"|"improve", loop?, baselineContent?, benchmark?, routes?}], noImprovePolicy?(default 30), remineOnEmpty? }
stopFileNopath whose existence stops the campaign — the operator stop signal
maxBatchesNosafety cap on valid FullTestBatches for this in-call run (default 3); not a completion state
Behavior5/5

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

No annotations are provided, so the description carries full burden. It transparently details rejection criteria (summary-only, early-stop, fake-metric, etc.), validation process, and the return value for missing loops. This far exceeds minimal disclosure.

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

Conciseness2/5

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

The description is a dense wall of text without bullet points or structure. While it front-loads the key 'AUTONOMOUS SUPERVISOR' label, the rest is a long sentence that could be broken into multiple sentences or lists for readability.

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?

Given the complexity of the tool and lack of output schema, the description covers the workflow, safety caps, validation, and return behavior. It is fairly complete, though a bit verbose.

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

Parameters3/5

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

Schema description coverage is 75% (3 of 4 params have descriptions). The tool description reiterates the purpose of maxBatches and stopFile but does not add new semantic details beyond the schema. Config parameter is described with a nested structure in the schema, and the description gives some context but no additional clarity.

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 the tool's purpose as an 'AUTONOMOUS SUPERVISOR' that drives a whole campaign end-to-end, listing specific phases (intake, work queue, mine/improve, etc.). It distinguishes itself from sibling tools like campaign_status or continue_run by being the main orchestrator.

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 includes opt-in condition (SUPER_LOOP_ALLOW_EXEC=1) and distinguishes between the in-call MCP run (bounded by maxBatches) and the standalone CLI. It does not explicitly list when not to use this tool relative to siblings, but provides clear context for when it is appropriate.

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/alexalexalex222/Loop-Factory-mcp-public'

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