Skip to main content
Glama
Sign In
grok

grok

by cigenb
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grok_spawn

Dispatch a bounded asynchronous subagent task to a local Grok instance with explicit readable/writable paths, prohibited actions, and acceptance criteria, then wait for or resume the session.

Instructions

派发给本机 Grok 4.7/high。完全访问权限，必须说明任务边界。允许 Grok 自行使用子代理。

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": {
      "prompt": "<prompt>",
      "scope": "<scope>"
    },
    "name": "grok_spawn"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNo
modelNo默认 grok-4.7（普通版）；仅明确指定时填写
scopeYes可读/可改路径、禁止动作、验收要求
effortNo默认 high
promptYes
wait_sNo
source_idNo可选的来源聊天 ID；Codex 自动取调用元数据，Claude 默认取启动时的会话 ID
session_idNo续问已有 Grok 会话；省略则新建

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations, the description does carry real weight here by disclosing that the agent runs with full access permissions and may spin up its own sub-agents — the key risk facts an agent needs. It stops short of explaining whether the call blocks or returns immediately, what happens on permission failures, or how the spawned run is later retrieved.

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 short, front-loaded sentences with no filler; the access-level warning comes early where it matters. It is arguably too terse for an 8-parameter tool, but nothing in it is wasted.

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 8-parameter, no-annotation, no-output-schema tool that launches a fully privileged agent, the description is thin: it never explains the async return (session id), how to follow up via grok_wait/grok_collect, or what the agent should expect back. The lifecycle context needed to use this correctly is missing.

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 coverage is only 63%, so the description must compensate, but it only restates model/effort defaults already implied by the parameter docs and re-states the 'scope' requirement. The undocumented parameters (cwd, prompt, wait_s) get no clarification, and wait_s in particular is semantically opaque without one.

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 names a concrete action and target: dispatching a task to a local Grok 4.7 instance at 'high' effort. It implicitly distinguishes itself from siblings (wait/status/steer/interrupt/collect) by being the launch step, though it never names those siblings 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?

Usage is only implied — 'dispatch a task to Grok' suggests this is how you start work, but there is no statement of when to choose this over grok_steer or how it relates to the collect/wait lifecycle. The one hard rule given ('must specify task boundaries') is a requirement, not a usage guideline.

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

Deploy Server

Other Tools