dolphin-anty-mcp

Screenshot the page

browser_screenshot

Read-only

Capture a page or specific element as a JPEG or PNG image to visually verify layout, canvas, or captcha-like elements that a text snapshot cannot convey.

Instructions

Capture the page as an image. Costs far more context than browser_snapshot, so reach for it only when the visual rendering matters — layout problems, canvas, captcha-looking elements, or verifying something a text tree cannot express.

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": {
      "profileId": "<profileId>"
    },
    "name": "browser_screenshot"
  }
}

Input Schema

Name	Required	Description	Default
`format`	No	JPEG is much smaller.	jpeg
`target`	No	Screenshot just this element.
`quality`	No	JPEG only.
`fullPage`	No	Capture the whole scrollable page.
`tabIndex`	No	Act on this tab just for this call, without changing which tab is active. Defaults to the active tab. To switch tabs for good, use browser_tabs with action 'select'.
`profileId`	Yes	Browser profile id, as passed to start_profile.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 1, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description adds valuable context by disclosing that this tool 'costs far more context' than browser_snapshot — a behavioral trait about resource usage not captured in annotations. While it doesn't detail return format, the cost disclosure and use-case framing add meaningful transparency beyond the 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.

Conciseness5/5

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

Two sentences, no wasted words. The first sentence states the purpose, the second provides usage context and a cost warning. Information is front-loaded and 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?

For a tool with a nested target object and no output schema, the description supplies strong selection guidance and cost context. It doesn't explain the return format, but the tool's purpose (screenshot as image) makes it inferable, and the rich schema covers invocation details. The description is complete enough for correct tool selection and basic usage.

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 description coverage is 100%, so the input schema already documents every parameter (format, target, quality, fullPage, tabIndex, profileId) with descriptions. The tool description itself adds no new parameter-level detail, so it meets the baseline but doesn't exceed it.

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 opens with 'Capture the page as an image' — a specific verb and resource that unambiguously states the tool's function. It also distinguishes itself from the sibling browser_snapshot by emphasizing that it is for visual rendering when a text tree is insufficient, making its role clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly contrasts with browser_snapshot and provides clear when-to-use guidance: use it only when visual rendering matters, with concrete examples (layout problems, canvas, captcha-like elements). It also warns about the cost, effectively telling the agent to prefer the cheaper alternative when possible.

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

Deploy Server