MCP Screenshot Server

annotate

Add boxes, arrows, text, highlights, and callouts to screenshots with precise positioning, anchors, and offsets for clear visual communication.

Instructions

Smart unified annotation tool with flexible positioning and anchor support.

Position formats:

Named: "top-left", "center", "bottom-right", "top-left-quarter", etc.
Percentage: "50%, 30%" (from top-left corner)
Pixels: "100px, 200px" or "100, 200" (absolute x, y)

Anchor controls which part of the annotation aligns to the position:

"top-left": annotation's top-left corner at position
"center": annotation's center at position (default)
"bottom-right": annotation's bottom-right corner at position

Offset allows fine-tuning: offset_x=10 moves 10px right, offset_y=-5 moves 5px up.

Examples:

annotate(img, "box", "50%,10%", width=200, height=50, anchor="top-center")
annotate(img, "text", "100px,50px", text="Label", anchor="top-left", offset_x=5)
annotate(img, "callout", "center", text="Note", offset_y=-20)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	No	Text content (for text/callout types)
`color`	No	Color	red
`width`	No	Width in pixels
`anchor`	No	Anchor point: which part of element aligns to position (top-left, center, bottom-right, etc.)	center
`height`	No	Height in pixels
`radius`	No	Radius for circles
`image_id`	Yes	ID of the image to annotate
`offset_x`	No	Horizontal offset in pixels (positive=right)
`offset_y`	No	Vertical offset in pixels (positive=down)
`position`	No	Position: named, percentage ('50%,30%'), or pixels ('100px,200px' or '100,200')	center
`font_size`	No	Font size for text
`line_width`	No	Line width
`auto_adjust`	No	Auto-adjust to stay within bounds
`end_position`	No	End position for arrows/lines
`annotation_type`	Yes	Type of annotation

Output Schema

TableJSON Schema

Name	Required	Description	Default
`message`	Yes	Status message
`image_id`	Yes	Image ID that was annotated

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations provided, the description must disclose behavior. It thoroughly explains position formats, anchor alignment, and offset direction, and provides examples. However, it does not mention side effects (e.g., whether the image is modified in place), return values, or behavior of auto_adjust. The description covers the core positioning mechanics but leaves some behavioral aspects implicit.

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?

The description is well-structured with clear sections for position, anchor, offset, and examples. It is somewhat long but every sentence contributes useful information. The front-loaded purpose is clear, and the examples are valuable. A minor point: the examples could be trimmed, but overall it is efficient.

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?

The description thoroughly covers positioning, anchor, and offset, which are the most complex aspects. However, it does not explain the meaning of each annotation_type (box, circle, etc.) nor the end_position parameter for arrows/lines, and it omits details about auto_adjust behavior. Given the tool's complexity and the output schema's existence, these gaps mean the description is not fully complete.

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% and the schema already describes each parameter. The description adds significant value by detailing the position formats (named, percentage, pixels), anchor semantics, and offset directions, and by showing combined usage in examples. This goes beyond the schema's brief descriptions.

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 it is a unified annotation tool with flexible positioning and anchor support. It lists the annotation types implicitly via examples and the schema enum, and the word 'unified' differentiates it from sibling tools like add_box, add_line, etc. This is specific and unambiguous.

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

Usage Guidelines2/5

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

The description gives examples but no explicit guidance on when to use this tool versus the specific add_* tools or precise_annotate. It does not mention alternatives or exclusion criteria. The 'unified' label implies it can replace them, but there is no explicit when-to-use or when-not-to-use guidance.

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