OmniSnap MCP

Ask the user to approve an action

propose_action

Destructive

Proposes clicks or typing in the browser, requiring user approval before acting. Use it to reach post-interaction states like open menus or validation errors for testing.

Instructions

Proposes clicking an element or typing into a field. The extension outlines the element and asks the user to approve; nothing happens unless they do. Use it to reach states that only exist after an interaction: an open menu, a validation error, the next step of a form. That is where most defects are. The user may decline. If they do, do not retry: ask them what they want instead.

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": {
      "action": "<action>"
    },
    "name": "propose_action"
  }
}

Input Schema

Name	Required	Description
`value`	No	For "type": the text to enter.
`action`	Yes	What to propose.
`element`	No	A number from the most recent annotate_interactive on this tab. Easier and safer than retyping a selector.
`selector`	No	A CSS selector, or the visible text.
`timeoutMs`	No	How long to wait for the user to answer.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.3Nov 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare destructiveHint=true, openWorldHint=true and non-idempotent, but the description adds the crucial behavioral fact those annotations cannot convey: the extension outlines the element and nothing executes until the user approves. The decline path and the no-retry rule are extra operational context beyond the annotations. It still doesn't describe what a declined proposal returns, which keeps it from a 5.

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?

Front-loaded with the core action, then the approval mechanic, then usage, then the decline rule — a sensible order. Six short sentences with little waste, though 'That is where most defects are' is motivational padding rather than load-bearing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter, destructive, user-gated interaction tool with no output schema, the definition covers what it does, what happens on approval, what happens on decline, and when it is worth invoking. The only unaddressed area, the shape of the response, is minor for a proposal 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%, so every parameter including the click/type enum, element index, selector, and timeout is already documented. The description only restates the action set (click or type) and adds no format or precedence guidance (e.g. element vs selector) beyond the schema. Baseline 3 applies.

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?

States a specific verb pair (proposes clicking / typing) and the resource (an element or field), which separates it from sibling interaction tools like hover, scroll_to, and focus_element. An agent immediately knows this is the user-gated interaction tool rather than a capture or navigation tool.

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 a concrete positive scenario (reach states that only exist after an interaction: open menus, validation errors, next form step) and an explicit negative rule (if the user declines, do not retry; ask what they want instead). It does not name a sibling alternative, but the when-to-use condition is unusually specific for this catalog.

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