Skip to main content
Glama

route

Dispatches work to agent peers such as Claude Code, Codex, ChatGPT, Slack, and GitHub by opening the correct VS Code/Cursor extension or CLI/API handoff for consult, launch, and status actions.

Instructions

Open the VS Code/Cursor extension for an agent peer (Claude Code, Codex/ChatGPT, Composer). Does not run claude -p or codex exec. Platform peers (github, railway, slack, …) still use CLI/API. Pass params.promptId to load a catalog prompt and params.memoryPacket to prepend shared MEMORY.

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": {
      "peer": "<peer>",
      "action": "<action>"
    },
    "name": "route"
  }
}

Input Schema

NameRequiredDescriptionDefault
peerYesPeer id: cursor, claude, codex, chatgpt, slack, github, railway, vercel, supabase, stripe, linear, ideation-hq
actionYesconsult = round-trip (opens the extension for agent peers), launch = start a job/post, handoff = open IDE UI, api = raw method, inbox = status
paramsNopromptId (catalog, e.g. chatgpt.plan), memoryPacket (shared MEMORY text), project_id (HQ job link), plus peer-specific fields.
promptNo
runtimeNo
transportNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description must carry behavioral weight, and it does: it discloses that the tool opens an IDE extension rather than spawning CLI subprocesses, and that promptId injects a catalog prompt while memoryPacket prepends shared MEMORY. Those are non-obvious side effects that the schema alone would not convey. It is silent on whether calls block for a round-trip response, what happens if the IDE is not running, and any permission requirements.

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?

Four short sentences, front-loaded with the core action and immediately followed by the negative scope that prevents misuse. Jargon density (peer, memoryPacket, catalog prompt) is high but each clause carries routing or behavior information. No filler sentences.

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?

For a six-parameter tool with a nested params object, no annotations, and no output schema, the description covers the routing decision and two key params but leaves runtime/transport/prompt semantics and any indication of what a call returns undocumented. It is enough to pick the tool, marginally enough to invoke it correctly.

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?

Coverage is 50%, and the description's parameter content (promptId loads a catalog prompt, memoryPacket prepends MEMORY) largely repeats what the schema's params description already states. The remaining parameters, prompt, runtime, and transport, are given no meaning in either place. That is adequate but not compensating for the coverage gap.

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 opening sentence gives a specific verb and resource ('Open the VS Code/Cursor extension for an agent peer') and enumerates the agent peers covered. It also fences the scope against adjacent behaviors ('Does not run claude -p or codex exec'), so an agent can distinguish this from call_cli/call_api. It falls short of 5 because the follow-on routing matrix (platform peers use CLI/API) adds breadth that dilutes the single crisp purpose.

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?

Explicit routing guidance is given: use this tool for agent peers (Claude Code, Codex/ChatGPT, Composer), and use CLI/API for platform peers (github, railway, slack). That is a clear when-to-use and when-not-to-use split against the sibling tools. There is no explicit exclusion for edge cases such as consulting a peer that is already running, which keeps it out of 5 territory.

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