Skip to main content
Glama

ios_lowlevel_telemetry

Reads low-level iOS/iPadOS telemetry over Tailscale DVT/Lockdownd, including processes, oslog, network, accessibility, and app launch/kill data for remote diagnostics.

Instructions

Read low-level iOS/iPadOS telemetry over Tailscale DVT/Lockdownd. Supported kind: summary, processes, ioregistry, schemes, oslog, network, accessibility, dvt_launch, dvt_kill.

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": {
      "kind": "<kind>"
    },
    "name": "ios_lowlevel_telemetry"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
filter_textNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden. Framing everything as 'Read' is actively misleading for the dvt_launch and dvt_kill kinds, which start and terminate processes; nothing warns that these mutate state or may require elevated access. The Tailscale/DVT/Lockdownd mention is genuine context, but the safety profile an agent most needs is absent.

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 short sentences, front-loaded with purpose before the capability list, with no filler. The kind list is a flat run-on that mixes read and mutating operations without grouping, which slightly undercuts the structure.

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?

An output schema exists, so return-shape explanation is not required, and the kind enumeration covers the required parameter. Still missing is any signal that two kinds are state-changing, plus any meaning for filter_text, which leaves an agent under-informed for a tool spanning both reads and process control.

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% and 'kind' has no enum in the schema, so the description's enumeration of the nine supported kinds is essential and adds real value. However, 'filter_text' is never mentioned at all, and there is no indication of which kinds honor the filter or what the kind strings map to behaviorally.

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 pairs a specific verb and resource ('Read low-level iOS/iPadOS telemetry') with the transport it uses ('Tailscale DVT/Lockdownd') and enumerates the capability set via the kind list. An agent can tell this is the deep-inspection tool rather than a UI-interaction tool like ios_tap or ios_screenshot. It stops short of 5 because it never names or contrasts a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The kind list implies what the tool can do, but there is no guidance on when to choose this over ios_status or ios_ui_dump, no prerequisites stated, and no when-not-to-use conditions. An agent must infer selection from capability names alone.

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