sommus-laptop

by Jashan-Mshadow

Overview Schema Source Related Servers Discussions Admin

Python

Local

save_browser_tab

Save a browser tab's file to disk, including PDFs behind logins. Then read the saved file to access protected content.

Instructions

Save a browser tab's file to disk (Cmd+S) — the way to get a PDF that sits behind a login.

Follow with read_pdf to read what was saved.

Args:
    tab: Tab number, window.tab, or text from its title or URL.
    folder: Where to save (default ~/Downloads).

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": {
      "tab": "<tab>"
    },
    "name": "save_browser_tab"
  }
}

Input Schema

Name	Required	Description	Default
`tab`	Yes
`folder`	No		~/Downloads

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 7, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only tell the agent it is a non-read, non-destructive operation. The description adds genuinely useful behavior: the save is driven via a Cmd+S keyboard shortcut (implying the browser/tab must be focused), and it discloses the save target default (~/Downloads). It does not cover overwrite behavior or focus prerequisites, hence not a 5.

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?

Two tightly written sentences front-load the purpose and workflow, followed by a compact args list that adds semantics rather than restating types. No filler, though the args block could be trimmed slightly.

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 2-param, no-output-schema tool, the description covers purpose, mechanism, both parameters, and the next step (read_pdf). It is nearly self-sufficient; only minor gaps like overwrite behavior and focus requirements remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the full burden and does so: 'tab' accepts a tab number, window.tab, or text from its title/URL, and 'folder' has a documented default of ~/Downloads. This adds meaning well beyond the bare schema types.

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 specific verb+resource ('Save a browser tab's file to disk') and immediately grounds it with the mechanism 'Cmd+S' and the goal 'get a PDF that sits behind a login'. This clearly distinguishes it from siblings like read_browser_tab or download_url. The only slight ambiguity is what 'the tab's file' refers to, but the login-gated-PDF clarification resolves it.

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?

Gives clear context for when to reach for this tool (extracting a PDF that requires authentication) and prescribes the follow-up workflow with read_pdf. It does not explicitly state when-not or contrast against download_url, but the usage context is concrete rather than implied.

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