Skip to main content
Glama

browser_scan

Scans the active page DOM and lists interactive elements with Vimium-style hints so AI agents can identify and click browser controls.

Instructions

DOM probe the active page; returns interactive elements with Vimium-style letter hints. Each entry carries backend/control_type/name/bbox/center/hint. Use protocol=bidi for Firefox Remote Agent.

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": "browser_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNonavigate first (default: skip)
portNo
protocolNocdp
host_headerNoBiDi Host header; use localhost:9222 through SSH forwarding
max_resultsNo
control_typeNo
url_containsNo
name_containsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: it reads the DOM of the active page, returns a structured element list (backend/control_type/name/bbox/center/hint), and supports a BiDi backend for Firefox with a host_header path for SSH forwarding. It omits side-effect disclosure — notably that supplying url causes navigation — and says nothing about failure modes when no page is active.

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?

Two tight sentences, front-loaded with the core action and output, followed by the protocol caveat. The slash-separated field enumeration ("backend/control_type/name/bbox/center/hint") is dense but earns its place by describing the return shape in the absence of an output schema.

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 compensates for the missing output schema by naming the returned fields, which is the most valuable thing it does. For an 8-parameter tool with zero annotations, though, it leaves most inputs and all preconditions (browser running, port/host expectations, filtering semantics) undocumented, so it is adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25% across 8 parameters, so the description must compensate, and it largely does not: url, port, max_results, control_type, url_contains, and name_contains are never explained in the description. The only added meaning is the protocol=bidi note for Firefox, which is modest against the documented gap; the field list describes return values rather than inputs.

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?

"DOM probe the active page; returns interactive elements with Vimium-style letter hints" names a specific verb (probe) and resource (active page DOM) and states the output shape, which makes it clearly distinguishable from browser_shot or vision_detect. It stops short of explicitly naming an alternative, so it is clear but not fully sibling-differentiated.

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

Usage Guidelines3/5

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

Usage is only implied: the agent can infer it should call this when it needs a list of clickable/typable elements. The one explicit directive, "Use protocol=bidi for Firefox Remote Agent," is protocol-selection guidance rather than when-to-use-vs-alternatives guidance, and there are no exclusions or prerequisites stated (e.g., that a browser must already be launched).

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