Skip to main content
Glama
archi-max

civ6-mcp

by archi-max
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

load_save_from_menu

Destructive

Load a saved Civilization VI game from the main menu by specifying a save name, or default to the most recent autosave. Uses OCR-guided clicks to navigate and load the save automatically.

Instructions

Navigate the main menu to load a save via OCR-guided clicking.

Args:
    save_name: Autosave name (e.g. "AutoSave_0221"). If not provided,
               loads the most recent autosave.

Requires the game to be running and at the main menu. Uses macOS Vision
OCR to find and click menu elements. Takes 30-90 seconds.

After loading, wait ~10 seconds then call get_game_overview to verify.

Requires pyobjc: uv pip install 'civ6-mcp[launcher]'

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
save_nameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.11

TDQS

A4.5/5.0
Behavior4/5

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

Discloses OCR-based clicking, duration, and required state. The annotation destructiveHint=true aligns with loading a save (state change). Adds value beyond annotations by detailing method and post-load steps.

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?

Three short paragraphs: purpose/parameter, requirements/timing, post-condition. Every sentence adds useful information without redundancy.

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?

Covers prerequisites, parameter, timing, and verification step. With an output schema present, return value details are not needed. Could mention error handling but overall complete for a load tool.

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

Parameters5/5

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

The single parameter 'save_name' is explained with a concrete example ('AutoSave_0221') and behavior when omitted ('loads the most recent autosave'). Schema coverage is 0%, so the description fully compensates.

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?

The description clearly states the action ('Navigate the main menu to load a save via OCR-guided clicking'), specifying the method (OCR) and context (main menu). It distinguishes from sibling tools like 'load_game_save' and 'restart_and_load' by focusing on menu-based OCR loading.

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?

Provides explicit prerequisites ('Requires the game to be running and at the main menu'), timing expectations (30-90 seconds), and a recommended follow-up action (call get_game_overview). Missing explicit when-not-to-use guidance but still offers clear context.

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