Skip to main content
Glama

chrome_use_read

Fetch any URL or the active browser tab as clean, agent-readable markdown, with options for raw HTML, heading outlines, links, or llms.txt content.

Instructions

Fetch a URL (or the active tab, if url is omitted) as agent-readable text/markdown.

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": "chrome_use_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNoReturn raw HTML instead of cleaned markdown.
urlNoURL to read; omit to read the active tab.
llmsNoRead from the site's llms.txt instead of the page itself.
forceNoWith tabId: act on a tab this session does not own (the user's own, or another session's), in place and in the background (--tab <handle> --force). Only when the user asked you to act on that tab; the result has forced: true and the tab's title and url.
linksNoAppend the page's links as absolute URLs (a `## Links` section; at most 100 unless maxLinks).
tabIdNoTarget tab id (e.g. t2), label, or targetId (--tab).
filterNoLiteral, ASCII-case-insensitive filter for page sections, llms links/sections or outline headings. Not a regex; page reads prefer matching headings and their descendants.
outlineNoReturn only the heading outline instead of full content.
sessionNoIsolated session name (chrome-use --session <name>). Each session gets its own tab group, browser tab and element refs. Omit it unless several agents share ONE MCP server — the session is otherwise derived per agent automatically. When you do share a server with sibling agents, pass a name unique to you on every call, or you will drive their tabs and invalidate their refs.
maxLinksNoCap for links (1-1000); implies links.
requireMdNoFail instead of falling back to raw text if markdown conversion is unavailable.
timeoutMsNoKill the underlying chrome-use process if it hasn't responded after this many ms (default 30000).
includeHiddenNoKeep text a person can't see on the active tab (a url is fetched without rendering and is never filtered) (off-screen, transparent, clipped, zero-size). Left out by default and counted in hiddenText/a note, because pages hide instructions aimed at agents there (--include-hidden).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.5.275
    • addedInput schema / properties / includeHidden
      Added value: +{
      +  "description": "Keep text a person can't see on the active tab (a url is fetched without rendering and is never filtered) (off-screen, transparent, clipped, zero-size). Left out by default and counted in hiddenText/a note, because pages hide instructions aimed at agents there (--include-hidden).",
      +  "type": "boolean"
      +}
  2. First observedv0.1.0

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description carries the full burden and delivers very little: it doesn't say fetching is read-only and side-effect free, that a URL fetch is unrendered while an active-tab read is filtered, that hidden text is stripped by default, or that the underlying process is killed at a timeout. The safety-relevant behaviors live only in the schema, so an agent reading the description alone would not know what changes state or what gets omitted.

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?

A single efficient sentence with the scope and the default front-loaded; nothing is wasted. It is arguably too compact given the tool's many modes, but that is a completeness issue rather than verbosity.

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

Completeness2/5

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

For a 13-parameter tool with no annotations and no output schema, one sentence is inadequate. The description never conveys the tool's multiple read modes (raw HTML, llms.txt, outline, links), the security-motivated hidden-text stripping, or the --force path that touches the user's own tabs, leaving the agent to discover tool-shaping behavior from parameter docs alone.

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 every one of the 13 parameters is documented in detail there, so the baseline is 3. The description itself adds no parameter meaning beyond restating the url-omission default.

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?

States a concrete verb ('Fetch') and resource ('a URL') and names the output form ('agent-readable text/markdown'), plus the default when url is omitted. What it lacks is any differentiation from siblings such as chrome_use_snapshot, which an agent must guess between.

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?

The parenthetical '(or the active tab, if url is omitted)' implies the default usage path, so the tool's basic invocation is inferable. But there is no explicit when-to-use/when-not, no routing to chrome_use_snapshot or chrome_use_open, and no hint about when the llms/outline/raw modes are appropriate.

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