Skip to main content
Glama
Sign In
dos2-gm-mcp

dos2-gm-mcp

by o-shabashov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Live layer readiness

dos2_live_status
Read-onlyIdempotent

Checks whether Divinity: Original Sin 2 is running and all live bridge prerequisites are ready—Script Extender, built/attached bridge mod, and heartbeat—before using live GM tools or after timeouts.

Instructions

Checks everything the live tools (dos2_live_*) need and reports what is missing: whether the game is running, whether Script Extender is installed next to the game and its settings, whether the bridge mod .pak is built, which campaigns have it attached, and whether the bridge's heartbeat is coming in (it writes one about every 2 seconds while a campaign is loaded in Game Master mode).

Read-only, no parameters. Call it before the first live tool of a session and whenever a live tool times out.
If the bridge is not built or attached, run dos2_bridge_install with the game closed. For file-level setup
(campaign list, Divine.exe) use dos2_status.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "dos2_live_status"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, and the description adds genuine context beyond them: the heartbeat cadence (~every 2 seconds while a campaign is loaded in Game Master mode), the fact that no parameters are needed, and the prerequisite that the game must be closed for the related install tool. It stops short of describing the shape of the returned report (e.g., a list of missing items vs. a status object), which is the one behavioral gap.

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?

Two paragraphs, both front-loaded: the check inventory first, then the call-timing and routing rules. The heartbeat parenthetical is the only aside and it carries real timing information rather than filler.

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

Completeness5/5

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

For a parameterless, non-destructive diagnostic with no output schema, the description covers what is inspected, when to invoke it, what failure implies, and which sibling performs the fix. Nothing an agent needs in order to decide to call it and act on the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so the baseline applies; the description consistently reinforces "Read-only, no parameters," which removes any doubt that arguments are required. No additional meaning is needed or possible here.

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?

Opens with a specific verb+resource ("Checks everything the live tools need and reports what is missing") and then enumerates the exact preconditions: game running, Script Extender installed with settings, bridge .pak built, campaigns attached, heartbeat present. It explicitly separates itself from dos2_status ("file-level setup") and from the dos2_live_* consumers, so an agent can place it among siblings without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit trigger conditions ("before the first live tool of a session and whenever a live tool times out") and a remediation route ("If the bridge is not built or attached, run dos2_bridge_install with the game closed"). It also names the correct alternative for out-of-scope work (dos2_status for campaign list / Divine.exe), covering both when-to-use and when-not-to-use.

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