Skip to main content
Glama

browser_save_page

Read-onlyIdempotent

Save the current page (or one element) into the workspace's files and get its file_id. format: 'pdf' (printed page; optional paper letter|legal|tabloid|a3|a4|a5 — default the page's own CSS size —, landscape, print_background, scale), 'html' (current DOM, or the outerHTML of ref), 'mhtml' (one self-contained offline copy with styles and images), 'png' or 'jpeg' (screenshot of the viewport, full_page, or ref), 'text' (visible text of the page or ref). ref is an aria-ref token or CSS selector (frame = CSS selector of the it lives in). Returns {file_id, name, mime, size, url, title}.

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": {
      "page_id": "<page_id>"
    },
    "name": "browser_save_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNo
frameNo
paperNo
scaleNo
formatNopdf
page_idYes
filenameNo
full_pageNo
landscapeNo
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
print_backgroundNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior beyond that: it states the exact return payload {file_id, name, mime, size, url, title} and the per-format semantics, which is real value given there is no output schema. However, it never acknowledges the mild tension between 'Save ... into the workspace's files' and readOnlyHint=true, and says nothing about size limits, quota, overwrite behavior, or whether an existing filename is replaced.

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?

The core action is front-loaded in the first clause, and the long parenthetical enumerating format behaviors is dense but earns its space by mapping each format to its use. The nested commas and dashes inside the parentheses make it harder to parse at a glance than an explicit per-format list would be.

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?

For an 11-parameter tool with no output schema, the definition does well on the format/rendering knobs and does state the return shape. It leaves the two undocumented parameters (filename, page_id) and the overwrite/collision behavior for the destination file unaddressed, which is the main gap for a tool that writes artifacts into a workspace.

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 description coverage is only 9%, so the description carries almost the entire load, and it does: format values, paper sizes, landscape, print_background, scale, full_page, ref (aria-ref token or CSS selector), and frame (CSS selector of the containing iframe) are all given meaning the bare schema does not provide. filename and page_id are left unexplained, and in_workspace is only covered by its own schema description, so it is not a complete compensation.

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?

"Save the current page (or one element) into the workspace's files and get its file_id" is a specific verb plus resource with an explicit scope (whole page or a single element) and an explicit outcome (file_id). It doesn't name or differentiate itself from the near-siblings browser_save_file or browser_save_session, so an agent must infer the boundary, which keeps it below a 5.

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 gives concrete selection guidance at the format level: 'mhtml' for 'one self-contained offline copy with styles and images', 'html' for 'current DOM', 'text' for 'visible text', 'png'/'jpeg' for viewport/full-page/ref screenshots, and 'pdf' for a printed page with paper/landscape/print_background/scale modifiers. What's missing is any statement about when to use this tool rather than the sibling save tools, or any caveat about when not to use it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.