Skip to main content
Glama
RPG Maker MZ Authoring MCP

RPG Maker MZ Authoring MCP

by NixonMSilva

Find walking path

find_path
Read-onlyIdempotent

Computes the shortest walking route between two map cells using RPG Maker MZ passage rules, returning move commands and a ready-to-use set_movement_route block.

Instructions

Shortest walking route between two cells using the engine's passage rules. Returns route command names (move_up, ...) and a ready-to-use set_movement_route block. With from={eventId} the event is the mover (blocked by any non-through event). adjacent=true (default when to is an event) stops next to the target and turns to face it.

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": {
      "mapId": "<mapId>",
      "from": "<from>",
      "to": "<to>"
    },
    "name": "find_path"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYes{x, y} or {eventId} (the event's position)
fromYes{x, y} or {eventId} (the event's position)
mapIdYes
assumeNoGame state used to pick each event's active page. Default: all switches/self switches OFF, variables 0, no items.
adjacentNo
ignoreEventsNoIgnore events (tiles only). Default false: blocking events count as obstacles.
ignoreEventIdsNoEvents that never block (e.g. NPCs that will have moved away)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral detail beyond them: passage rules drive the result, event movers are blocked unless through, and adjacent mode stops beside the target and turns to face it. It does not explain what happens when no path exists, which is the main remaining 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?

Three tight sentences, front-loaded with purpose then return value then parameter behavior. Dense but readable; the parenthetical 'adjacent=true (default when `to` is an event)' is slightly compressed but still parseable.

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?

For a 7-parameter tool with nested position objects and no output schema, the description covers purpose, return shape, and the two non-obvious parameters. Only the failure path (no route found) and the game-state `assume` object go unmentioned, and the latter is documented in the schema.

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

Parameters4/5

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

Schema coverage is 71%, and the description still adds meaning the schema lacks: it explains the {eventId} form of `from` and its blocking semantics, and defines `adjacent` (undescribed in the schema) including its default and its side effect of turning to face. The `assume`, `ignoreEvents` and `ignoreEventIds` parameters rely on the schema text alone.

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 — 'Shortest walking route between two cells using the engine's passage rules' — and additionally names what it returns (route command names plus a set_movement_route block). No sibling tool performs pathfinding, and the phrasing makes that scope unmistakable.

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?

Gives conditional usage cues: use from={eventId} when the event itself is the mover (and note it is blocked by non-through events), and adjacent defaults to true when `to` is an event. However, it never states when to choose this over alternatives, nor any exclusion such as maps that are too large or unreachable targets.

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