Skip to main content
Glama

start_parallel_workers

Start multiple Claude Code workers at once for independent features, each running in its own tmux session to run parallel coding tasks.

Instructions

Start multiple Claude Code workers simultaneously for independent features. Each worker runs in its own tmux session.

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>",
      "featureIds": "<featureIds>"
    },
    "name": "start_parallel_workers"
  }
}

Input Schema

NameRequiredDescriptionDefault
featureIdsYesArray of feature IDs to start (e.g., ['feature-1', 'feature-2']). Maximum 10 workers at once.
projectDirYesAbsolute path to the project directory
customPromptsNoOptional: Map of feature IDs to custom prompts (e.g., {'feature-1': 'Additional context...'})

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries the full burden. It does add one real behavioral trait (each worker gets its own tmux session), but says nothing about side effects of spawning up to 10 processes, what happens if some workers fail to start, prerequisite state for the project directory, or whether the call blocks until workers are running.

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?

Two short sentences, front-loaded with the action and the isolation model. No filler, nothing to trim.

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

Completeness2/5

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

This is a multi-process spawning operation with no annotations and no output schema, yet the description never says what the call returns (session IDs? status?), how partial failures are reported, or what preconditions the project must satisfy. For a tool with this much side-effect surface, that leaves an agent under-informed before invoking it.

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%, including the 10-worker cap on featureIds and the customPrompts map shape, so the schema already handles parameter meaning. The description adds nothing beyond it, which is the baseline 3 case rather than a deficiency.

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: start multiple workers simultaneously, scoped to 'independent features,' and notes the execution model (own tmux session). It does not differentiate itself from close siblings such as start_worker or start_continuous_worker, so an agent must infer the batching distinction on its own.

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?

'For independent features' implies the when-to-use condition — parallel, non-conflicting work — but there is no explicit exclusion (e.g., dependent features) and no named alternative such as start_worker for a single feature. Usage is implied rather than stated.

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