Skip to main content
Glama
Sign In

LinkGents

by ai.linkgents
OverviewDiscussionsAdmin

Start a remote agent

start_remote_agent

Ask to start a Claude Code run on a teammate's machine in a folder they allowed, for a ticket or a short task. It runs code there: confirm it with your owner first. The machine owner may have to approve it.

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": {
      "machine": "<machine>",
      "folder": "<folder>"
    },
    "name": "start_remote_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskNoWhat to do, in plain words; or give ticket
branchNoOptional new branch, made from origin/development
folderYesFolder name or id, from list_remote_machines
ticketNoTicket key such as "LG-12"; or give task
machineYesMachine handle or grant id, from list_remote_machines

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare non-readonly, non-destructive, non-idempotent, and closed-world behavior. The description adds important context beyond that: it runs code remotely, requires owner confirmation, and may need machine-owner approval. It does not spell out non-idempotence or outcome details, but it meaningfully exceeds the annotations.

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?

Three short sentences, front-loaded with the action and scope, followed by approval caveats. Every sentence contributes and there is no filler.

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?

For a remote code-execution mutation tool, the description covers purpose, target constraints, and permission/approval prerequisites. It omits return behavior and branch implications, but there is no output schema and annotations cover the basic safety profile.

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 description coverage is 100%, so the schema already explains all five parameters. The description reinforces that the folder must be one the teammate allowed and that the task may be a ticket, but it does not add meaning for the machine or branch parameters beyond the schema.

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: start a Claude Code run on a teammate's machine in a folder they allowed, for a ticket or short task. An agent can distinguish this from listing machines or asking a general question, though no sibling tool 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 Guidelines4/5

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

Gives clear usage context: use it for a ticket or short task on a teammate's allowed folder, and confirm with the owner first. It lacks explicit alternatives or when-not-to-use guidance, so it is strong but not complete.

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

All LinkGents toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources