Skip to main content
Glama
Sign In

secondstrike

by io.github.KyleClouthier
OverviewDiscussionsAdmin

build_world

Read-onlyIdempotent

BUILD A WORLD: designs a living world (a calm world-history sandbox where nations rise, split, sign pacts and fall on their own) and returns its share link, which anyone can open to watch it run, and the cleaned spec. Nothing is created on the server and no token is needed. To sit in the world yourself, pass the returned spec as "world" to join_war with room "new", then start_war: you lead one nation and the others are run by the house.

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": "build_world"
  }
}

Input Schema

NameRequiredDescriptionDefault
seasNoRising seas in years mode: the great low deltas turn to marsh from 2050.
yearNoOptional: the year the world starts in (years mode).
pactsNoAllow alliances (default true).
rulesNocalm: no doomsday clock, no nukes, endless (default); war: the full war rules; mayhem: cheap early nukes.
startNo"normal" (patches of land), "borders" (every country on its real 2026 borders), "pixel" (one cell each), or a date pack: era1914, era1939, era1962, era1991, era0117, era1279, era1453, era1648, era1815, era1871, era1945, era2100.
titleNoOptional: the world's title, up to 60 characters.
yearsNoYears mode: one minute is one year, leaders age and die (default false).
groupsNoOptional: your own empires, each {"name": "...", "color": [r,g,b], "members": ["ISO3", ...]} folded from real countries (the first member leads). Starts on real borders.
reliefNoReal mountains and forests: the Alps, Himalaya, Andes... slow every march.
stableNoNo civil wars, no coups.
nationsNoHow many nations (default 42; 200 with a date pack or real borders).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false; the description reinforces this by stating nothing is created on the server. It adds useful behavioral detail the annotations cannot convey — that a live share link is produced and that the world runs autonomously. It doesn't address how long the share link persists or whether repeated identical calls yield the same world, which is the only gap.

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?

Front-loaded with the core action and output, then the workflow. Dense but each sentence earns its place; the parenthetical sandbox description is the only slightly expendable clause.

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 11 optional parameters and no output schema, the description correctly states what is returned (share link plus cleaned spec) and gives the end-to-end usage path. It doesn't state that the tool can be called with no arguments to get a default world, which would have fully closed the loop for a zero-required-parameter tool.

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% and each of the 11 parameters is well documented in the schema itself. The description mentions the concept of a "spec" and the join_war handoff but adds no format or default guidance beyond the schema, so the baseline of 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 — designs a world-history sandbox with nations that rise, split, sign pacts and fall — plus what it returns (share link and cleaned spec). This is clearly distinct from siblings like join_war, start_war, and get_state.

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?

Explicitly names the follow-up path: pass the returned spec as "world" to join_war with room "new", then start_war, with the agent leading one nation against house-run nations. It also rules out a misconception up front — nothing is created server-side and no token is needed — so the agent knows this needs no auth setup.

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

All secondstrike toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources