Skip to main content
Glama

Take a Recordful screenshot

take_screenshot

Capture a tab, screen, window, or area, then open it in Recordful’s screenshot editor to style it with wallpaper, padding, and shadow for saving or sharing.

Instructions

Take a screenshot with Recordful and open it in Recordful's screenshot editor, styled (wallpaper, padding, shadow). By default the tab handed to Recordful in Chrome; with source screen, window or area, the Recordful desktop app takes it from the desktop. Use this when the user wants a screenshot to keep or share; use screenshot only to look at the page yourself. Returns no image.

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": "take_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
lookNoOnly if the user asked for a look: "3d" for a 3D tilt, or a preset (Clean, Window, Glass, Spotlight, Midnight, Bold, None). Leave it out otherwise: the default puts the screenshot on a wallpaper that suits its colours, with rounded corners and a shadow.
modeNo"visible" (default): what is on screen. "page": the whole page, scrolled and stitched.
sourceNo"tab" (default): the tab handed to Recordful in Chrome. With the Recordful desktop app: "screen" a whole display, "window" one window by name (see list_windows), "area" one the user drags.
windowNoFor source "window": part of the window title or app name, e.g. "Figma" or "Pricing".
displayNoFor source "screen": 1 for the first display, or "main" (the default).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds genuinely new behavior: it opens an editor UI, it depends on which Chrome tab was handed over, and critically "Returns no image" — telling the agent not to expect image data. It does not clarify what, if anything, is persisted or whether repeated calls create duplicates.

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 action and the styling behavior, then usage routing, then the return note. Every sentence earns its place, though the phrase "By default the tab handed to Recordful in Chrome" is grammatically clipped and takes a re-read.

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?

A 5-parameter, 0-required tool with no output schema and full schema coverage — the description supplies the missing pieces: which invocation context (Chrome tab vs desktop app), where output goes (editor), and that no image is returned. Minor gaps remain around persistence and whether the screenshot is saved to a library.

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 every parameter already carries a full enum/format explanation, so the baseline is 3. The description reinforces the defaults for source (tab) and look (omit unless asked) but adds little syntax or constraint detail beyond what the schema states.

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 ("Take a screenshot with Recordful") plus the post-action behavior (opens in Recordful's screenshot editor, styled with wallpaper/padding/shadow). It explicitly distinguishes itself from the sibling "screenshot" tool, so an agent can choose without opening either schema.

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?

Gives explicit when-to-use guidance ("when the user wants a screenshot to keep or share") and names the alternative with its own condition ("use screenshot only to look at the page yourself"). It also explains the context split between the Chrome tab flow and the desktop app for screen/window/area sources.

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