Skip to main content
Glama

Update the MiSTer

mister_run_update
Destructive

Triggers a system update on a MiSTer device to refresh cores, scripts, and Linux files; it refuses while a game is running and may reboot the device.

Instructions

<use_case> Trigger update_all.sh to update cores, scripts, and Linux system files. </use_case> <important_notes>

  • DESTRUCTIVE: Runs on screen for several minutes and may trigger a system reboot.

  • Refused if a game is currently playing.

  • Rate-limited to once per hour to prevent reboot loops. </important_notes>

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": {
      "host": "<host>",
      "confirm": "<confirm>"
    },
    "name": "mister_run_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesMiSTer name from mister_get_status. Required: there's no default for this.
confirmYesMust be true: you've confirmed with the user that it may reboot.

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 already flag destructive=true and idempotent=false, but the description adds genuinely new behavior: the update runs on screen for several minutes, may trigger a reboot, is blocked during gameplay, and is rate-limited to one call per hour. These are operational facts the agent cannot derive from the annotations or schema.

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 tagged sections, use case first and warnings second, with no filler. Every bullet carries an actionable constraint (destructive, blocked during play, rate limit).

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?

An output schema exists so return values need no explanation, and the description covers the remaining risk surface: duration, possible reboot, gameplay precondition, and throttling. Nothing an agent needs before calling a destructive, non-idempotent operation is missing.

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 coverage is 100% and both parameters are fully documented in the schema, including that 'host' comes from mister_get_status and that 'confirm' must be true after user consent. The description adds nothing about the parameters, 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 concrete verb and resource: 'Trigger update_all.sh to update cores, scripts, and Linux system files.' The scope (cores, scripts, Linux system files) distinguishes it from every sibling, none of which perform updates.

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 usable preconditions — refused while a game is playing, limited to once per hour — which tells the agent when the call will fail. It stops short of naming an alternative (e.g. return to menu first, or a status check), so the agent must infer the recovery path.

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