Skip to main content
Glama

Look at a window

look
Read-onlyIdempotent

Inspect a Windows app window in the background without bringing it forward: read UI Automation roles, names, values and states, capture covered windows, and OCR image-only interfaces for later actions.

Instructions

See a window in the background, without bringing it forward: UI Automation tree (roles, names, ids, values, states) and, with mode image or both, a native capture that works even when the window is covered (WebP, at most 2000 px; unchanged since the last image sent: not attached again, mode image always attaches it). A window with almost no tree (Tk, canvas, game: fewer than 6 elements) also gets the text of its image read by OCR (ocr.lines: text, point, screenshotId), clicked with point + screenshotId. Selects that window for act; an observation serves one act and expires after 60 s. Returns its observation id: pass it to act (required from protocol 2026-07-28).

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": "look"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNotext (UI Automation tree, default), image (native capture), both
imageNoWith region: screenshotId of the full native image the region is in pixels of (required from protocol 2026-07-28); refused once a newer image of that window replaced it
marksNoNumbers drawn on the image of mode both, each the index of its tree line: none (default), auto (unnamed controls), all
regionNo[x1, y1, x2, y2] in pixels of the last native image of this window: that area enlarged up to 2x (small text); its own screenshotId takes points
windowNoWindow id from windows, or a unique part of its title or app; omitted: the window of the last look

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.7.4
    • addedInput schema / properties / image
      Added value: +{
      +  "description": "With region: screenshotId of the full native image the region is in pixels of (required from protocol 2026-07-28); refused once a newer image of that window replaced it",
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare read-only/idempotent, but the description adds substantial behavior: capture works when the window is covered, unchanged images are not re-attached in mode text/both while mode image always attaches, OCR fallback for sparse trees (<6 elements) yielding ocr.lines, observation expiry, one-observation-per-act lifetime, and the protocol-version requirement for the observation id. This is far beyond what annotations provide.

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?

Purpose is front-loaded and every clause carries information, but the prose is dense and parenthetical-heavy, mixing capture, OCR, selection, and protocol rules into long run-on sentences. Appropriate length for the tool's complexity, with some readability cost.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description explains the return value (observation id), how to use it, and its 60-second lifetime. It covers the key gotchas: image de-duplication, covered-window capture, OCR fallback, protocol-version requirement, and window defaulting. Nothing an agent needs to invoke it correctly is missing.

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 100%, so baseline is 3, but the description adds cross-parameter meaning: 'with mode image or both' native capture, 'mode image always attaches it' vs the dedup behavior, region enlarging up to 2x and its own screenshotId for points, and the OCR behavior tied to sparse windows. It still leaves marks/full region syntax to the schema, but the semantic relationships are valuable.

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 action ('See a window in the background, without bringing it forward') and resource, and immediately differentiates itself from the sibling act by describing it as an observation that selects a window for act. An agent can tell this is a non-intrusive inspection tool without opening the schema.

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?

Explicitly routes usage relative to act: 'Selects that window for act; an observation serves one act and expires after 60 s. Returns its observation id: pass it to act (required from protocol 2026-07-28).' It also explains the default window param (last look). It doesn't contrast with windows/launch, which would complete the routing picture.

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