OmniSnap MCP

Capture the page

capture_page

Read-only

Capture the active tab or full scrollable page as an image so you can verify layout, check fixes visually, or see what the user describes.

Instructions

Takes a screenshot of the active tab and returns it as an image the model can see. Captures the full scrollable page by default, including pages that scroll inside a panel. Use it to check layout, verify a fix visually, or see what the user is describing.

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": "capture_page"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	No	"full" stitches the whole page, "viewport" takes only what is on screen.	full
`viewport`	No	Render the page at a breakpoint before capturing. "current" uses the window as it is.	current

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.3Nov 11, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior: the return is an image the model can see, and full-page capture stitches content that scrolls inside a panel. It does not mention size limits, latency, or how the image is delivered, so it adds moderate rather than rich context.

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?

Three short sentences, front-loaded with what the tool does and its default behavior, followed by usage cases. Every sentence carries information; nothing is redundant.

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?

With no output schema, the description correctly states that the result is a viewable image, and it documents the default capture scope. It omits the region mode and the viewport breakpoint option, but those are fully described in the schema, so the definition is nearly complete for a two-parameter read-only tool.

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 100%, so the baseline is 3. The description goes beyond the schema by explaining that full-page capture is the default and that it includes pages scrolling inside a panel, which clarifies the practical effect of mode="full" beyond the schema's "stitches the whole page." The region mode and viewport breakpoint parameter are left to the schema.

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: "Takes a screenshot of the active tab and returns it as an image the model can see." It also clarifies the default scope (full scrollable page, including inner-scroll panels), which separates it from a viewport-only capture. It does not name or distinguish itself from siblings like capture_element or capture_matrix, so it stops short of a 5.

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?

Gives concrete when-to-use cases: check layout, verify a fix visually, or see what the user is describing. There is no when-not guidance and no explicit routing to capture_element or capture_matrix for element- or matrix-level captures, so the agent must infer alternatives.

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