Skip to main content
Glama

configure_plan_mode

Configures worker plan mode so agents analyze the codebase and create an auto-approved implementation plan before coding. Set thresholds, step limits, and required plan sections.

Instructions

Configure worker plan mode. When enabled, workers analyze the codebase and produce a plan before implementing. Plans are auto-approved by the orchestrator.

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_plan_mode"
  }
}

Input Schema

NameRequiredDescriptionDefault
enabledNoEnable/disable plan mode globally (default: true)
maxStepsNoMaximum steps allowed in a plan (default: 20)
projectDirYesAbsolute path to the project directory
requireFileListNoRequire file list in plans (default: true)
maxReplanAttemptsNoMaximum re-plan attempts before fallback (default: 2)
complexityThresholdNoMinimum complexity score to trigger plan mode (default: 30)
requireTestStrategyNoRequire test strategy in plans (default: true)
requireRiskAssessmentNoRequire risk assessment in plans (default: true)

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 provided, the description carries the full behavioral burden and does disclose one genuinely non-obvious trait: plans are auto-approved by the orchestrator, so no human gate exists. It does not say whether changes apply to already-running workers, whether the config persists across sessions, or whether settings are scoped globally or per project — a real gap given `projectDir` is required while `enabled` is described as 'global'.

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 with zero filler, front-loading the purpose and then the effect of enabling it. The opening sentence slightly restates the tool name, but the following sentences each add new information rather than repeating structured fields.

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 an 8-parameter configuration tool with no output schema and no annotations, the description covers the core toggle's semantics and the auto-approval behavior, while the schema covers the tuning knobs. Missing pieces an agent would want: persistence/scope of the config, effect on in-flight workers, and what a response looks like after applying settings.

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%, so every parameter including bounds (maxSteps 1-50, maxReplanAttempts 0-5, complexityThreshold 0-100) and defaults is already documented in structured data. The description adds conceptual context for why a plan step budget or complexity threshold exists, but no parameter-level detail beyond the schema. Baseline 3 applies.

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?

States a specific verb and resource ('Configure worker plan mode') and immediately explains what the mode does: workers analyze the codebase and produce a plan before implementing. An agent can tell this is a configuration toggle rather than an action tool. It does not explicitly distinguish itself from the configure_* siblings (ralph_loop, reviews, verification), leaving that inference to the name.

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?

Usage is implied rather than stated: the description conveys that enabling this gates implementation behind a plan, which tells an agent roughly when the setting matters. There is no explicit when-to-enable vs when-to-leave-disabled guidance, no mention of prerequisites, and no routing to alternative configuration tools for related behaviors.

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