Skip to main content
Glama

Read the page

browser_snapshot
Read-only

Captures the current page as a compact tree of headings, text, and actionable refs, covering three screens around the viewport or the full page with whole_page.

Instructions

The current page as a compact tree of headings, text and elements with refs (e12) to act on: three screens around the viewport, or everything with whole_page. Refs stay valid while their element is on the page.

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_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
whole_pageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds real behavioral context: the default capture window is roughly three screens around the viewport, refs are stable while the element remains on the page, and refs are the handles used to act. It does not explain what happens to refs after navigation or scroll, which is the remaining operational question.

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?

Two short sentences, zero filler. The return shape comes first and the scoping parameter follows, which is the right front-loading for a read tool.

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 one-parameter read tool with annotations covering safety and no output schema, this covers what the agent needs: what comes back, default scope, and ref lifetime. A sentence on whether refs survive navigation or that a fresh snapshot is needed after page changes would close the last gap.

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% for the single boolean whole_page, so the description must carry the meaning, and it does: default is the viewport neighborhood, whole_page means everything. The contrast is clear enough to pick a value without inspecting the schema.

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 names a specific resource and form: the current page as a compact tree of headings, text and elements with refs like e12. That distinguishes it from siblings such as browser_screenshot or browser_get_text, though it never explicitly says which sibling to prefer.

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?

It gives scope guidance (default is three screens around the viewport; whole_page captures everything), which implies you use this to see the page and obtain refs. It never states when to choose it over browser_find, browser_get_text, or browser_query, so the routing is left to inference.

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