Skip to main content
Glama

launch_game

Launch Deadlock, optionally straight into a local map with the full match HUD.

Instructions

Launch Deadlock, optionally straight into a local map with the full match HUD.

map: 'new_player_basics' (sandbox / practice range — verified), 'dl_hideout', 'dl_midtown'. ('hero_testing' crashes the game even unmodded.)

Default: run deadlock.exe directly through umu-run with the game's own Proton prefix (no Steam launch prompt, no shader pre-caching; Steam must be running for login). Always adds -console -condebug -dev -novid (-condebug writes console.log, which the bridge replies through). extra_args is split like a shell command line. Mounts the dev addon for this session (if that fails, the game is not launched); it is unmounted automatically when the game exits. via_steam=True uses steam -applaunch (Steam asks the user to confirm custom arguments).

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": "launch_game"
  }
}

Input Schema

NameRequiredDescriptionDefault
mapNo
via_steamNo
extra_argsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses the injected flags (-console -condebug -dev -novid), the condebug logging side effect the bridge reads, the dev addon mount/unmount lifecycle, and the failure mode where a mount failure aborts the launch. The notable gap is whether the call blocks until the game exits or returns immediately, and what happens if a session is already active.

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?

Front-loaded with the one-line purpose, followed by grouped details (map options, default behavior, flags, mount lifecycle, Steam alternative). The parenthetical asides and the crash warning all carry actionable information, so nothing reads as 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?

Output schema exists, so return values need no explanation, and the description covers side effects, flag injection, addon lifecycle, and the Steam confirmation prompt. It is only missing invocation-model details (blocking vs. async, behavior when the game is already running) that an agent would want before calling.

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?

Schema coverage is 0%, so the description must compensate, and it largely does: map values are enumerated with reliability notes, via_steam is defined by the underlying mechanism (steam -applaunch), and extra_args is defined as shell-like splitting appended to the fixed flag set. The map list is presented as partial and the anyOf/string schema means the description is the only source of valid values, which keeps it short of a 5.

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 and resource ("Launch Deadlock") plus the optional scope ("straight into a local map with the full match HUD"). It is plainly distinguishable from siblings like quit_game and the addon/bridge management tools, which it merely references as side effects.

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?

Explains the default launch path (umu-run with the game's own Proton prefix) and the concrete alternative via_steam=True with its consequence (Steam asks the user to confirm custom arguments). It also gives a prerequisite ("Steam must be running for login") and flags which map values are safe vs. crashy, though it never states when NOT to use this tool (e.g., a game already running).

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