Skip to main content
Glama

Back up saves

mister_backup_saves
Idempotent

Creates timestamped local backups of MiSTer game saves and save states, using hard links for unchanged files and rate limiting to avoid SD card and network overload.

Instructions

<use_case> Create a timestamped local backup of game saves and save states from the MiSTer. </use_case> <important_notes>

  • Rate-limited to prevent SD card and network IOPS exhaustion.

  • Uses hard links for unchanged files to save disk space.

  • Requires configured backup_dir and SSH connectivity. </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_backup_saves"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNoMiSTer name from mister_get_status. Omit when the call already says which (a ref does).
dry_runNoCount what would be copied, write nothing.

Output Schema

NameRequiredDescriptionDefault
hostYes
filesYes
copiedYes
linkedYes
prunedYes
outcomeYes
snapshotYes
bytes_copiedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare a non-read-only, idempotent, non-destructive operation, so the bar is lower, and the description still adds genuinely non-obvious behavior: rate limiting to protect SD/network IOPS, hard links for unchanged files to save space, and the backup_dir/SSH prerequisites. It stops short of describing failure behavior or where the timestamped backup lands, keeping it below a 5.

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 short blocks with the purpose front-loaded in use_case and three dense bullets under important_notes. Every sentence contributes new information; there is no restatement of the title or schema.

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?

An output schema exists, so return values need not be explained, and the description covers the operational constraints that matter for a mutation-plus-IO tool. What is missing is modest: recovery/partial-failure behavior and where backups are written relative to backup_dir.

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?

Both parameters are fully documented in the schema (100% coverage), so the schema carries the burden and the baseline of 3 applies. The description adds no further meaning about host resolution or what dry_run output looks like beyond 'count what would be copied' already in the schema.

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: 'Create a timestamped local backup of game saves and save states from the MiSTer.' The scope (local, timestamped, saves plus save states) is precise enough that an agent knows exactly what the call produces without opening the schema.

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

Usage Guidelines3/5

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

The important_notes give prerequisites — a configured backup_dir and working SSH connectivity — which is real usage context. However, there is no explicit statement of when to prefer this over other actions, no when-not-to-use case, and no guidance on using dry_run first, so usage is only implied.

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