Skip to main content
Glama

eyes_see_desktop

Capture a desktop screen or region and extract visible text with OCR, processed in memory; if no OCR engine is found, returns the install command instead of failing silently.

Instructions

See the desktop: capture a screen (or a region) and OCR its visible text.

Screenshots are processed in memory and never written to disk. The OCR engine is discovered, never assumed: without one you get the exact install command instead of a silent failure. region = [left, top, width, height] in physical pixels. as_image=True attaches ONE downscaled image of the screen (vision mode, on request).

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": "eyes_see_desktop"
  }
}

Input Schema

NameRequiredDescriptionDefault
regionNo
monitorNo
as_imageNo
languageNoeng
providerNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the privacy property (screenshots processed in memory, never written to disk), the failure mode (exact install command returned instead of a silent failure), and that only one downscaled image is attached. It omits rate limits and what happens with multiple monitors, which keeps it below 5.

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 core action in the first sentence, then privacy, failure behavior, region format, and the vision-mode caveat. The wording is tight and each sentence carries information; minor rhetorical flourish ('discovered, never assumed') is acceptable but slightly padded.

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

Completeness3/5

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

No output schema and no annotations, so the description must do everything, and it covers behavior and failure modes well. However, three of five parameters receive no explanation and the return shape of the OCR text (structure, truncation, per-monitor aggregation) is unaddressed, leaving gaps for a 5-parameter tool.

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 coverage is 0% across 5 parameters, so the description must compensate. It fully specifies `region` format and units ('[left, top, width, height] in physical pixels') and explains `as_image`, but leaves `monitor`, `language`, and `provider` entirely undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'capture a screen (or a region) and OCR its visible text.' The 'desktop' framing in the name and description implicitly separates it from eyes_see_browser, but the description never explicitly names or contrasts that sibling. An agent can tell what the tool does, though not with maximum certainty which sibling to prefer.

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?

Implied usage is clear (grab text off the desktop), and it gives one concrete opt-in rule: 'as_image=True attaches ONE downscaled image of the screen (vision mode, on request).' There is no explicit when-to-use/when-not guidance relative to eyes_see_browser or desktop_inspect, so selection between siblings is left to inference.

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