OmniSnap MCP

Numbered map of interactive elements

annotate_interactive

Read-only

Capture an annotated screenshot that outlines and numbers every interactive element, with a table mapping each number to its best selector and stability score. Pick a number to target elements reliably before acting.

Instructions

Returns a screenshot with every interactive element outlined and numbered, plus a table mapping each number to its best selector and a stability score. This is the tool to use before acting on a page: look at the image, pick a number, then use that number's selector. Far more reliable than guessing a selector from the DOM.

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": "annotate_interactive"
  }
}

Input Schema

Name	Required	Description	Default
`include`	No	"controls" covers buttons, inputs and selects; "all" adds links and landmarks.	controls
`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

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered by structured data. With no output schema, the description usefully explains the return payload (image plus mapping table with stability scores), but it omits operational traits an agent would care about here, such as whether the viewport render mutates or restores page state, cost/latency of a full-page annotation pass, or behavior on pages that are not loaded.

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 sentences, front-loaded with the output description, then the intended workflow, then the comparative rationale. Every sentence carries distinct information and none restates the name or title.

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 only two fully documented optional parameters, no output schema, and safe-read annotations, the description covers what the agent needs: what comes back, how to use it, and why. The remaining gap is environmental preconditions (page must be loaded, which tab/frame is annotated), which matters for an open-world capture tool.

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% and both enums are documented inline in the schema, so the baseline is 3. The description adds nothing about 'include' or 'viewport' semantics beyond what the schema already states, and its phrase 'every interactive element' even sits slightly at odds with the default include=controls.

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?

The description names the resource and the concrete artifact produced: a screenshot with every interactive element outlined and numbered, plus a table of numbers, selectors, and stability scores. It implicitly separates itself from raw-DOM selector guessing, but never names or contrasts with siblings such as capture_page, inspect_element, or collect_selectors, so an agent must infer the boundary from behavior alone.

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?

There is explicit when-to-use guidance: 'This is the tool to use before acting on a page,' followed by a concrete workflow (look at the image, pick a number, use that selector). What is missing is a when-not clause or a named alternative for cases where a plain capture or a selector list would suffice.

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