Skip to main content
Glama

start_continuous_worker

Launch a Claude Code worker that processes queued features sequentially in a loop, reducing startup overhead by reusing one worker across multiple tasks.

Instructions

Start a Claude Code worker that processes multiple features sequentially in a loop. The worker picks up new tasks from a queue, reducing startup overhead. Inspired by the infinite-loop pattern from 'Building a C compiler with parallel Claudes'.

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>",
      "featureId": "<featureId>"
    },
    "name": "start_continuous_worker"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxTasksNoMaximum features before worker exits (default: 10)
workerIdNoWorker identifier (default: auto-generated)
featureIdYesFirst feature to work on
projectDirYesAbsolute path to the project directory

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral load. It discloses the looping behavior, queue pickup, reduced startup overhead, and (via schema) that the worker exits after maxTasks. It omits whether the call returns immediately or blocks until completion, what happens when the queue is empty, failure handling, and cost/resource implications.

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?

Front-loaded with the core action in the first sentence, and the queue/startup-overhead detail is useful. The closing attribution to 'Building a C compiler with parallel Claudes' is decorative and does not help an agent decide or invoke correctly.

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?

No output schema exists, so the description should clarify what a caller receives (worker ID? immediate return vs. blocking?). For a long-running loop-launching tool, the sync/async semantics and lifecycle are the key missing piece, though the parameter surface is fully covered by the schema.

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 all four parameters (projectDir, featureId, maxTasks, workerId) are already documented in the schema. The description adds no parameter-level meaning beyond what the schema provides, so 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 ('Start a Claude Code worker') plus the distinguishing behavior: sequential looping over multiple features and pulling new tasks from a queue. It differentiates implicitly from parallel/one-shot siblings but never names them, so the reader must infer the contrast.

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

Usage Guidelines2/5

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

The description explains the benefit ('reducing startup overhead') but gives no explicit when-to-use or when-not-to-use guidance, and does not point to alternatives like start_worker, start_parallel_workers, or start_ralph_loop despite those being the obvious competing choices.

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