Visionaire Engine

Overview Schema Source Related Servers Discussions Admin

annotated_screenshot

Capture a screenshot of the page with numbered marks linked to element uids, or crop a specific element with optional padding and zoom. Use for spatial layout issues, overlapping elements, or identifying small components.

Instructions

Screenshot in two modes: an overview with numbered marks burned in, where mark N equals uid eN (mark 17 = e17); or an element-scoped crop via clipTo (uid|selector|x,y) with optional padding, scale (0.5..4 zoom for tiny elements), and annotate:false for a clean unlabeled crop. Use when text tools are not enough and you need to SEE the page while keeping pixels tied to elements — spatial or visual-layout questions ('things overlap', 'the layout looks off'), to zoom in on one small element, or to confirm which element is which. Then target elements by their uid.

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": "annotated_screenshot"
  }
}

Input Schema

Name	Required	Description
`uids`	No	Uids to mark; default: top ~25 visible interactive/landmark elements
`scale`	No	clipTo only: zoom factor for the crop, clamped 0.5..4 (2 = double size)
`clipTo`	No	Crop the screenshot to this element's border box instead of the whole viewport (target by uid \| selector \| x+y). Pairs with padding, scale, and annotate. Takes precedence over region and fullPage — pick ONE capture mode.
`region`	No	Clip to this viewport rectangle (CSS px). Ignored when clipTo is given (clipTo wins).
`padding`	No	clipTo only: extra pixels of margin around the cropped element on every side
`annotate`	No	When false, burn in NO marks/labels — a clean crop so labels never cover the target
`fullPage`	No	Capture the whole page height. Ignored when clipTo or region is given (they win).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.1Jul 7, 2026

TDQS

A4.3/5.0

Behavior4/5

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

No annotations provided, so description carries full burden. Explains two modes, mark numbering, parameter interactions (clipTo precedence), and annotate option. Implied read-only, no destructive side effects mentioned.

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?

Single paragraph packs all essential information, front-loading modes and usage. Could be slightly more structured (e.g., bullet points) but clear and efficient.

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?

Covers both capture modes, all parameters, and use cases. Output format not mentioned but likely standard for screenshots. Sufficient for agent to understand tool selection and invocation.

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%, but description adds context: modes, precedence rules, mark numbering convention, and usage scenarios for parameters like scale, padding, annotate.

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?

Clearly states two screenshot modes (overview with numbered marks tied to uids, element-scoped crop via clipTo). Specifies use cases for visual/spatial questions, zooming, element confirmation, distinguishing from sibling tools.

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 says when to use ('when text tools are not enough... spatial or visual-layout questions'), but does not explicitly list when not to use or compare to many close siblings like inspect_element or pick_element.

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