Skip to main content
Glama

Take a screenshot

mister_take_screenshot

Capture the current MiSTer video output as a PNG screenshot and return it inline, with rate limiting to avoid SD card write exhaustion.

Instructions

<use_case> Capture the current video output of the MiSTer as an image. </use_case> <important_notes>

  • Rate-limited to avoid SD card write exhaustion.

  • Saves PNG to /media/fat/screenshots and returns inline ImageContent. </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_take_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNoMiSTer name from mister_get_status. Omit when the call already says which (a ref does).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that the call is rate-limited to avoid SD card write exhaustion, that a PNG is persisted to /media/fat/screenshots, and that the image is returned inline as ImageContent. That explains why readOnlyHint is false despite this being a 'capture' operation — a genuinely useful addition. It stops short of saying what happens when the rate limit trips (error vs. throttled retry).

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?

Content is front-loaded into a one-line use case followed by two short notes, and every line carries information. The XML-style wrapper tags cost a few tokens for only modest structural benefit, so it is not maximally tight.

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 one-optional-parameter tool with no output schema, the definition covers purpose, side effect, storage location, and return type, while annotations cover safety flags. The only gap is the failure mode when the rate limit is hit.

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?

There is a single optional parameter and schema coverage is 100%; the schema already documents that 'host' is a MiSTer name from mister_get_status and may be omitted. The description adds nothing about host resolution, 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?

The description gives a specific verb and resource: 'Capture the current video output of the MiSTer as an image.' No sibling in the list performs screenshots, so the tool is immediately distinguishable.

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 <use_case> block implies the usage context (grabbing whatever is currently displayed), but there is no explicit when-to-use/when-not guidance or comparison to alternatives such as mister_get_status. Usage is implied rather than stated.

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