Skip to main content
Glama
chrome-remote-debugging-mcp

chrome-remote-debugging-mcp

by danilin-em

browse

Open a URL to get a compact, screen-reader-readable page view with numbered element refs for interacting with pages in Chrome.

Instructions

Open url and return a readable view of the page, with numbered refs.

The view is built from Chrome's accessibility tree — what a screen reader would announce — not from HTML, so it is compact enough to act on. Every interactive element gets a #N ref usable with browse_act.

Opens a new tab when tab_id is omitted; pass the returned tab_id to browse_act / browse_view. Returns {"tab_id", "url", "view", "refs"} or {"error": ...}.

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": {
      "url": "<url>"
    },
    "name": "browse"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
tab_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses that the view comes from Chrome's accessibility tree rather than HTML, that it is compact, that a new tab is created when ``tab_id`` is omitted, and it documents the return shape including an error variant. It does not cover failures like navigation timeouts, JS-heavy pages, or auth-gated content.

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?

Four short paragraphs, front-loaded with the action and result, then rationale, then the ref contract, then the return shape. Every sentence adds information; nothing is padding.

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?

For a two-parameter tool with no annotations and no output schema, the definition covers purpose, the ref mechanism, tab lifecycle, and the return payload, which is enough for correct invocation. It is slightly thin on failure behavior and on how the returned refs expire or change after interaction.

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 0%, so the description must compensate, and it largely does: ``url`` is the page to open and ``tab_id`` controls whether an existing tab is reused or a new one is opened, with the returned ``tab_id`` feeding later calls. It does not state the expected URL format (absolute vs relative) or what a stale/invalid ``tab_id`` does.

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?

Opens with a specific verb and resource ('Open ``url`` and return a readable view of the page') and names the concrete artifact produced (numbered refs). It also distinguishes itself from siblings by naming ``browse_act`` and ``browse_view`` as downstream consumers of the refs and tab_id.

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?

The description explains the workflow: call this to get a view and refs, then pass ``tab_id``/``#N`` refs to ``browse_act`` or ``browse_view``, and states that omitting ``tab_id`` opens a new tab. It stops short of an explicit 'use this instead of navigate' rule, so there is a small gap around sibling selection.

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