Skip to main content
Glama

browser_extract

Render pages in Chrome to extract text and links, optionally limited to a CSS selector, so you can retrieve content hidden behind JavaScript.

Instructions

Render a page in Chrome and extract text + links (optionally a CSS selector only).

Use for content hidden behind JavaScript. selector example: "main", "#app", "table.results". Without a selector the whole body text is returned.

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": "browser_extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
wait_msNo
selectorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.6/5.0
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 it does disclose the Chrome rendering path, the selector-scoping behavior, and the default of returning whole body text. It says nothing about timeout/error behavior, wait semantics for dynamic content, truncation of large pages, or whether a browser session already open matters. Useful but incomplete for an unannotated tool.

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?

Three tight sentences with the core capability front-loaded and the selector examples placed where they are needed. The parenthetical "(optionally a CSS selector only)" is slightly ambiguous about whether text extraction is bypassed when a selector is set.

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?

With no output schema and no annotations, the description does cover the two return shapes (text plus links, or body text when no selector). It leaves out failure modes and the meaning of the wait parameter, which matter for a browser-rendering tool that can time out.

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 coverage is 0%, so the description must compensate, and it does for `selector` by giving concrete examples ("main", "#app", "table.results") and stating the no-selector default. `wait_ms` — the parameter most likely to cause failures on slow pages — is never mentioned, and `url` formatting is unexplained.

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 pairs concrete verbs with a concrete resource: render a page in Chrome and extract text plus links. That clearly separates it from siblings like browser_screenshot or browser_eval. It never names a sibling explicitly, so differentiation is implicit rather than stated.

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?

"Use for content hidden behind JavaScript" is a real selection criterion that tells an agent when this tool beats a static fetch. There are no exclusions and no named alternatives, so the when-not side is left entirely to inference.

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