DevEyes

Overview Schema Source Related Servers Discussions Admin

screenshot

Capture and optimize screenshots from any URL for LLM consumption with automatic resizing, compression, and console error capture.

Instructions

Capture a screenshot from any URL (typically localhost) with automatic optimization for LLM consumption. Handles image resizing and compression to stay within Claude/LLM limits. Captures console errors and warnings.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "screenshot"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Full URL to capture (e.g., http://localhost:3000)
`viewport`	No	Viewport preset name or custom WxH (e.g., "mobile", "tablet", "desktop", "1280x720"). Available: mobile, mobile-lg, tablet, tablet-landscape, desktop, desktop-lg, desktop-hd	desktop
`fullPage`	No	Capture full scrollable page instead of viewport only
`waitFor`	No	Wait condition before capture: networkIdle (default), domStable, load, or none	networkIdle
`waitForSelector`	No	CSS selector to wait for before capture (optional)
`save`	No	Save screenshot to local .deveyes/screenshots/ folder. Use this if the image is not displaying in your client. Can be set as default via DEVEYES_SAVE_SCREENSHOTS=true env variable.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Jun 13, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries full burden. It discloses automatic resizing/compression for LLM limits, and capture of console errors/warnings. While it doesn't mention rate limits or auth, the behavioral traits are well-covered for a read-only capture tool.

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

Conciseness5/5

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

The description is three sentences with no repetition or fluff. Information is front-loaded: the first sentence states the main action, followed by optimization and error capture. Every sentence earns its place.

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?

Considering 6 parameters (all documented in schema) and no output schema, the description adds useful context on optimization and error output. It does not specify return format, but for a screenshot tool that is often implicit. Overall sufficient for the complexity.

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 100% with descriptions for all 6 parameters. The description adds only general context (optimization) beyond schema, so baseline 3 is appropriate. No significant additional semantics are introduced.

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 clearly states the tool's purpose: 'Capture a screenshot from any URL' with specification of typical use on localhost and automatic optimization for LLM consumption. It effectively distinguishes the action and resource.

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 description implies usage when an LLM-optimized screenshot is needed but lacks explicit when-not-to-use guidance or mention of alternatives. No sibling tools exist, but context of when to avoid (e.g., if raw image needed) is missing.

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

screenshotA