Skip to main content
Glama

Diagnose PassTunnel

diagnose
Read-only

Checks the PassTunnel installation and all profiles without connecting to find why sign-ins fail, covering app version, helper, network, credentials, and clock drift.

Instructions

Checks the PassTunnel installation and every profile without connecting: app version and location, helper installed/enabled/outdated, whether this computer is online and over what kind of network (from the system's own view, nothing is contacted), and per profile whether the configuration, server and saved credentials are in place (never their values) and the last clock measurement (a FortiGate gateway's time, taken after it rejected a sign-in). Start here when something does not work. A clock off by 15 s or more makes one-time codes fail.

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": "diagnose"
  }
}

Input Schema

NameRequiredDescriptionDefault
check_clockNoAlso ask the NTP server this computer is set up with how far this computer's clock is off. This contacts that server, so set it only when the user asked to check the clock.

Output Schema

NameRequiredDescriptionDefault
buildNo
clockNo
helperYes
networkNo
versionYes
app_pathYes
profilesYes
clock_errorNo
secret_storeNo
macos_versionNo
in_applicationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: states that nothing is contacted for the network view, that credential values are never returned, and that check_clock is the sole exception that contacts the NTP server. It also flags the mutating side of the diagnostic (clock skew causing one-time code failures). The only tension is openWorldHint=false against the opt-in NTP contact, but the description discloses that opt-in explicitly rather than contradicting the default behavior.

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?

Front-loaded with the core action, then the enumerated checks, then the entry-point advice and the clock caveat. Dense but every clause carries information; the parenthetical 'from the system's own view, nothing is contacted' could be tightened slightly.

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

Completeness5/5

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

Covers default behavior, the one optional-parameter side effect, privacy guarantees about credentials, and when to invoke it. An output schema exists, so return-shape detail is correctly omitted; nothing an agent needs to call it correctly is missing.

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?

With 100% schema coverage the baseline is 3, but the description adds a usage constraint the schema lacks: set check_clock only when the user asked to check the clock, and explains the resulting external contact. This is real decision-support beyond the parameter's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (Checks/diagnose) and enumerates the exact scope: app version and location, helper state, connectivity view, per-profile configuration/server/credential presence, and last clock measurement. The phrase 'without connecting' and 'every profile' separate it from get_status (single status) and list_profiles (list only), so an agent can pick it without opening any schema.

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?

'Start here when something does not work' gives an explicit triage entry point, and the clock note explains an actionable follow-up condition. There is no explicit when-not guidance (e.g., use get_logs for historical failures), but the read-only, no-connect framing implies its lane clearly.

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

Deploy Server

Other Tools