Skip to main content
Glama

join_execution

Register an external worker in a heads-down run and receive a one-time agent token for worker tools; include a task_id to create or reuse its worktree and return the task card.

Instructions

Register an external worker (for example this chat, or another host) in a heads-down run. Returns an agent_token ONCE: pass it with execution_id to every worker tool (read_blackboard, claim_task, lease, post_update, run_command, submit_work, escalate, spawn_subtasks, await_subtasks). With task_id, the task's worktree is created (or reused) and its task card returned. External workers are not sandboxed: their leases are checked when they submit.

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": {
      "execution_id": "<execution_id>",
      "agent": "<agent>"
    },
    "name": "join_execution"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoAn existing team of the contract.
agentYesYour agent id in the run.
task_idNo
execution_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4.1/5.0
Behavior4/5

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

Adds substantial behavior beyond annotations: agent_token is returned ONCE (must be captured), task_id triggers worktree creation or reuse plus a task card return, and external workers are not sandboxed with leases checked only at submission. These are meaningful operational traits not derivable from readOnlyHint=false/idempotentHint=false.

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, then the token contract, then the task_id side effect. Dense and mostly earned, though the nine-tool enumeration is long and the paragraph reads as a run-on rather than clearly separated statements.

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

Completeness4/5

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

No output schema exists, and the description compensates by describing both return values (one-time agent_token and the task card). With 4 params and 50% coverage, only the team parameter is left without explanation, a minor gap for a registration tool.

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 coverage is 50%, with team and agent described in-schema. The description clarifies task_id's side effects (worktree created/reused, task card returned) and execution_id's role (paired with agent_token for all worker tools), but the team parameter's purpose remains unexplained in both description and schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Register an external worker ... in a heads-down run.' It also names the two modes of operation (bare registration vs. with task_id for worktree creation), so an agent can distinguish it from control_execution and execution_status sibling tools.

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

Usage Guidelines4/5

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

Gives clear usage context: 'for example this chat, or another host' for external workers, and directs the agent to pass the returned agent_token with execution_id to every worker tool, listing them. No explicit exclusions or when-not-to-use guidance, keeping it below a 5.

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