Skip to main content
Glama

codebuddy_start_development

Start a background coding job on a remote CodeBuddy Code machine with a specified working directory, prompt, model, and reasoning effort; unattended runs use an isolated worktree and auto mode.

Instructions

Start a background coding job through CodeBuddy Code. Supports an explicit model and reasoning effort. The target working directory is on the CodeBuddy machine. Unattended jobs default to auto mode in an isolated worktree; never request bypassPermissions.

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": {
      "cwd": "<cwd>",
      "prompt": "<prompt>"
    },
    "name": "codebuddy_start_development"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdYes
nameNo
agentNo
modelNo
effortNo
promptYes
useWorktreeNo
permissionModeNoauto

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 carries the full behavioral burden. It discloses background execution, isolated worktree behavior, default auto mode, and the bypassPermissions restriction, but it omits return behavior, job identifiers, and how to monitor or interact with the job after starting it.

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?

The description is four short, front-loaded sentences with no wasted wording. Each sentence adds either purpose, operational context, or a safety constraint.

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?

For an eight-parameter tool with no annotations, no output schema, and zero schema description coverage, this is incomplete. It should explain the required prompt, the agent/name fields, and enough about the job lifecycle or return value for an agent to use it correctly.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must explain all eight parameters. It adds meaning for the working directory, model, reasoning effort, permission mode, and worktree behavior, but leaves name, agent, and the required prompt largely unexplained, and does not document enum meanings.

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 states a specific verb and resource: starting a background coding job through CodeBuddy Code. The mention that the working directory is on the CodeBuddy machine helps distinguish it from local-coding siblings, though no sibling is named explicitly.

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?

It gives useful context for unattended jobs, including the default auto mode and worktree isolation, plus a clear prohibition on bypassPermissions. However, it does not explicitly say when to choose this over workbuddy_start_development or related job-monitoring tools.

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