Skip to main content
Glama

ie_screenshot

Capture PNG screenshots of IE-mode pages, elements, or windows, including modal dialogs, and save them to a session folder.

Instructions

Capture PNG screenshots. scope=page (default) is the driver's view of the page; scope=element (by/value, the default when value is given) one element; scope=window renders the session's windows as the user sees them with PrintWindow: first the main window (or the attached tab's browser window), then every open modal HTML dialog and script alert/confirm/prompt, bottom-most to top-most, one image each, plus a text item that lists them (a system dialog is listed, never captured; a minimized window is reported, not restored). Window shots need no driver, so they work while a dialog blocks the page; target=hwnd: (from ie_windows) captures that one window of this session only. A window IE paints itself can come out blank: say so rather than guess. save_path, a bare file name, also saves it in the session's screenshots folder (several images: name, name-2, name-3, ...); saved files are kept after ie_close.

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": "ie_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
byNoelement locator type (for element screenshot)
frameNo
scopeNopage, element or window (default: window with a target, element with value, else page)
valueNoelement locator value (for element screenshot)
targetNoscope=window only: hwnd:<n>, one window of this session (from ie_windows or a NOTICE); no other form is accepted
timeoutNoseconds to wait for the element (default 10)
no_inlineNoreturn confirmation text instead of the image blob
save_pathNobare file name, e.g. shot.png; omit it to not save (an empty string is an error)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly: ordering of window captures (bottom-most to top-most), that a system dialog is listed but never captured, that a minimized window is reported rather than restored, that IE-painted windows may come out blank and should be reported not guessed, and that saved files survive ie_close. This is exactly the side-effect and failure-mode detail an agent cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The leading sentence is properly front-loaded, but the remainder is a single dense wall of parenthetical clauses and semicolon-joined asides about PrintWindow ordering, dialog listing, and blank windows. The content is valuable, yet it is not structured into scannable segments, which slows parsing.

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 an 8-parameter tool with no annotations and no output schema, the description covers the important behavior: what each scope returns, how window captures are enumerated, the accompanying text item, and file persistence. Minor gaps remain around no_inline and timeout, but those are low-risk and partly covered by 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 already 88%, so the schema does most of the work, but the description adds real meaning: target accepts only hwnd:<n> sourced from ie_windows, save_path is a bare file name that also writes into the session screenshots folder with name-2/name-3 collision naming, and multi-image cases are explained. It stops short of explaining no_inline or frame, which the schema covers only briefly.

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 ('Capture PNG screenshots') and then enumerates the three scope modes with concrete semantics. An agent can tell exactly what this produces and how it differs from the navigation/inspection siblings.

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 selection logic for each scope, including the implicit defaults (element when value is given, else page) and the key condition that window shots need no driver so they work while a dialog blocks the page. It does not explicitly name a competing tool to use instead, but there is no other screenshot sibling and the when-to-use conditions are clear.

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