Skip to main content
Glama

body_privacy_preflight

Check installed browsers, VPN status, local-model setup, free RAM, and privacy warnings before starting a private session; optionally show IP without changing anything.

Instructions

Check the privacy posture BEFORE a private session starts.

Reports: which browsers are installed, whether the VPN app is installed and open, whether a LOCAL model is configured, the free RAM, and the warnings - including the one about your reasoning model still being remote (a warning, never a block). It changes nothing and asks for no IP unless you ask for it.

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": "body_privacy_preflight"
  }
}

Input Schema

NameRequiredDescriptionDefault
show_ipNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations provided, the description carries the full behavioral burden and largely meets it: it declares the tool is side-effect free ('changes nothing'), makes no network/IP lookup by default, and that the remote-model warning is advisory not blocking. It does not describe failure modes (e.g. behavior when the VPN is missing) or latency, which keeps it short of 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?

The report list is front-loaded and the constraints follow, with no filler sentences. The parenthetical 'including the one about your reasoning model still being remote (a warning, never a block)' is slightly verbose and could be tightened.

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 read-only preflight with one optional flag and no output schema or annotations, the description is sufficient: an agent knows what is checked, that calling it is harmless, and that results may include warnings. Only the concrete shape of the report (field names, IP format when show_ip is true) is left implicit.

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% with a single optional parameter, so the description has to compensate. It does partially: 'asks for no IP unless you ask for it' conveys the meaning and default of show_ip without naming it or stating the returned IP format. Useful semantic hint, but not fully explicit.

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?

Uses a specific verb + resource ('Check the privacy posture') and a precise timing ('BEFORE a private session starts'), then enumerates the exact facts it reports (browsers installed, VPN app installed/open, local model configured, free RAM, warnings). This clearly separates it from sibling session tools such as privacy_session_start/open, even though no sibling is named explicitly.

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 'BEFORE a private session starts' framing gives a clear condition for when to call it, and the note about the remote-reasoning-model warning clarifies what it is not (a gate). It does not state exclusions or point to an explicit alternative, but the temporal cue is strong enough to guide selection.

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