Skip to main content
Glama

configure_ralph_loop

Configures Ralph Loop mode to give workers fresh context each iteration, load state from disk, and support hours- or days-long autonomous coding sessions.

Instructions

Configure Ralph Loop execution mode. When enabled, workers get fresh context each iteration with state loaded from filesystem. Supports hours/days-long autonomous sessions.

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": {
      "projectDir": "<projectDir>"
    },
    "name": "configure_ralph_loop"
  }
}

Input Schema

NameRequiredDescriptionDefault
enabledNoEnable/disable Ralph Loop globally (default: false)
projectDirYesAbsolute path to the project directory
maxIterationsNoMaximum iterations per feature (default: 50)
stopOnCompleteNoStop when .done file detected (default: true)
verifyBeforeStopNoRun verification before stopping (default: true)
maxDurationMinutesNoMaximum duration in minutes per feature (default: 480 = 8 hours)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the core behavioral model: workers get fresh context each iteration and reload state from the filesystem. However, it omits operational traits an agent needs for a configuration mutation, such as whether changes apply to already-running sessions, whether settings persist, or how maxIterations and maxDurationMinutes interact.

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

Conciseness4/5

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

Three short sentences, front-loaded with the purpose before the explanatory detail, with essentially no filler. It could be marginally tighter, but nothing is padded or redundant.

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

Completeness3/5

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

For a six-parameter configuration tool with no output schema, the definition covers the what and some of the why, but leaves gaps on outcomes (does it return the applied config?), persistence, and effect timing on running loops. It is adequate rather than complete.

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 100% and every parameter already carries its own description with defaults and bounds, so the schema does the heavy lifting. The description adds no parameter-level detail beyond the vague reference to long sessions, which is the expected baseline-3 outcome here.

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

Purpose4/5

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

The description names a specific verb and resource ("Configure Ralph Loop execution mode") and then explains what that mode actually does. An agent can grasp the purpose without opening the schema, though the definition never explicitly contrasts itself with the sibling 'start_ralph_loop', leaving the configure-vs-start distinction to inference from the names.

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

Usage Guidelines3/5

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

"Supports hours/days-long autonomous sessions" implies the appropriate scenario (long-running autonomous work) without stating when to use this versus starting or resetting a loop. There are no exclusions, prerequisites, or sequencing guidance such as whether configuration must precede a start.

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