Skip to main content
Glama

clawbridge_dispatch

Dispatches one queued task to a remote CodeBuddy worker using its registered repository path, sending an isolated worktree request. Uncertain gateway receipts become unknown and are not retried automatically.

Instructions

Dispatch one queued task to CodeBuddy using its registered remote repository path. The worker receives an isolated worktree request. An uncertain gateway receipt becomes unknown and is never automatically retried.

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": {
      "taskId": "<taskId>"
    },
    "name": "clawbridge_dispatch"
  }
}

Input Schema

NameRequiredDescriptionDefault
effortNo
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: an isolated worktree is requested, and an uncertain gateway receipt becomes 'unknown' and is never auto-retried — critical at-most-once semantics an agent needs before retrying. It omits what state the task moves to, whether the call is destructive, and what authorization is required.

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 lean sentences, front-loaded with the action and resource, followed by the worktree behavior and the no-retry rule. Every sentence adds information; slight cost is that the third sentence's 'gateway receipt' terminology arrives without definition.

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?

No output schema and no annotations, so the description should cover more: it does not say what dispatch returns (a job id? a receipt handle?) or what the agent should do when the receipt is 'unknown'. Combined with an undocumented 'effort' parameter, the definition is thin for a state-mutating dispatch tool.

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 compensate, and it only loosely does: 'one queued task' hints at taskId but never states the expected identifier form. The 'effort' enum parameter (minimal through max) is not mentioned at all, leaving the agent to infer its effect from the enum values alone.

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: 'Dispatch one queued task to CodeBuddy', plus the mechanism (registered remote repository path). It distinguishes dispatch from generic job creation by tying it to an already-queued task, though it never names a sibling such as clawbridge_submit or codebuddy_start_development to contrast with.

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?

The phrase 'one queued task' implies a precondition (a task must already be queued) and 'never automatically retried' implies the agent should not re-issue the call itself. But there is no explicit when-to-use vs when-not, and no statement of what to do instead if the task is not queued or the receipt is unknown.

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