Skip to main content
Glama

take_screenshot

Capture the current RPG Maker MV playtest frame through the authenticated MCP bridge and save it as a PNG for inspection or QA evidence without shell commands.

Instructions

Capture the current RPG Maker MV playtest frame through the authenticated MCP bridge and save it as a PNG under .mcp-cache/screenshots/. Returns {path, bytes, mimeType, name} so the image can be inspected or attached as QA evidence without shell commands. Requires manage_system actions install_bridge_plugin, bridge_start, and playtest first. Optional name becomes a safe filename prefix; each capture keeps a timestamp. manage_system {action:"bridge_screenshot"} remains available as a compatibility alias.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNomapId: with y, a normal screen view centred on this tile instead of the whole map
yNo
nameNoOptional safe filename prefix, e.g. boss-room or collision-proof
mapIdNoRender this map headless as the engine draws it, with no game running (PNG under .mcp-cache/renders/). Needs the optional playwright-core and a cached Chromium (npx playwright install chromium-headless-shell, or RPGMAKER_MCP_CHROMIUM).
switchesNomapId: switch IDs to turn ON first, to see later event pages
runEventsNomapId: let autorun/parallel events run before the shot (default false)
timeoutMsNoHow long to wait for the game response in milliseconds (default 15000)
showEventsNomapId: draw event sprites (default true)
showPlayerNomapId: draw the player (default: hidden for the whole map, shown for a view)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.19.0

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations (which only declare readOnly/idempotent/destructive=false), the description discloses the save location, the exact return shape {path, bytes, mimeType, name}, and that each capture keeps a timestamp so repeated calls accumulate files — consistent with idempotentHint=false. It does not cover failure modes when the bridge is not running.

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 dense sentences with the core action and destination front-loaded, followed by prerequisites and then the alias. Every sentence carries information, though the alias sentence could be trimmed.

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 9 optional parameters and no output schema, the description compensates by explaining the return object and naming conventions. The notable gap is that `mapId` switches the tool into a headless map-render mode (different output dir, no running game, Playwright dependency) that the description's 'requires playtest first' framing does not acknowledge.

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 89%, so the schema already carries most parameter meaning. The description only adds that `name` is a filename prefix and that timestamps are appended — useful but marginal, and it never reconciles the `mapId` headless-render mode that writes to a different directory.

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 states a specific verb and resource ('Capture the current RPG Maker MV playtest frame ... save it as a PNG') and names the destination directory. It is readily distinguishable from siblings like record_video (still frame) and manage_system, and it explicitly names the compatibility alias.

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?

It gives concrete prerequisites ('Requires manage_system actions install_bridge_plugin, bridge_start, and playtest first') and points to an alternative invocation path (bridge_screenshot alias). It does not, however, state when a still capture is preferable to record_video, so an agent still infers the choice.

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