Skip to main content
Glama

Launch a game or core

mister_launch
Idempotent

Launch a MiSTer FPGA game by reference or open a system core without media; requires returning to the menu if another game is running.

Instructions

<use_case> Launch a game via ref or open a core without media on a MiSTer FPGA. </use_case> <important_notes>

  • Refuses to launch while another game is active; call mister_return_to_menu first.

  • Rate-limited to prevent rapid FPGA bitstream reconfiguration cycling.

  • Signals game start to Pixelcade marquees and MQTT play tracking. </important_notes>

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": "mister_launch"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameNoA game ref from mister_search_games or mister_play_history, e.g. 'Family Room/4812'.
hostNoMiSTer name from mister_get_status. Omit when the call already says which (a ref does).
systemNoInstead of a game: a system id from mister_list_systems, to open its core with no game.

Output Schema

NameRequiredDescriptionDefault
hostYes
detailYes
outcomeYes
warningsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare the safety profile (non-read-only, idempotent, non-destructive); the description adds the state precondition that blocks invocation, the existence of rate limiting against bitstream cycling, and the downstream side effects on Pixelcade marquees and MQTT play tracking. Those are exactly the traits an agent cannot get from structured fields and would otherwise be surprised by.

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?

The content is dense and front-loaded: purpose first, then three bulleted constraints that each carry distinct information. The XML-style <use_case>/<important_notes> scaffolding is slightly heavier than three plain sentences would need, but no sentence is wasteful.

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?

With an output schema present, return values need no explanation, and the preconditions plus side effects round out what an agent must know before calling. The one remaining gap is what actually happens when the rate limit is hit (error vs. queued) or whether a successful launch terminates/replaces anything, which matters for a non-read-only toggle.

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 each parameter (game, host, system) is already fully documented including provenance of the refs and the "instead of a game" relationship. The description's phrase "via ref or open a core without media" restates that split but adds no syntax, format, or mutual-exclusion detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ("Launch a game via ref or open a core without media on a MiSTer FPGA") and explicitly covers the two invocation modes the schema exposes (game ref vs. bare core/system). A sibling like mister_return_to_menu is clearly a different operation, so the agent can route without ambiguity.

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 a concrete when-not condition (refuses while another game is active) plus the corrective alternative ("call mister_return_to_menu first"), and points at the sibling tools that produce each input type (mister_search_games, mister_play_history, mister_list_systems). Both the selection and the prerequisite path are spelled out rather than inferred.

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