Skip to main content
Glama

iphone_start_agent

Idempotent

Starts WebDriverAgent on a connected iPhone and establishes the required connection for other iPhone actions; call it when no connection is reported or before using iPhone tools.

Instructions

Start WebDriverAgent on the iPhone and connect to it – required before any other iphone_* action.

Call it when iphone_status or another tool reports no connection. It is safe to call again: if the
agent already runs it just reports the connection. Starting takes 10–90 s, works over cable or Wi-Fi
and needs the iPhone unlocked; if it is locked, the result says so and the user must unlock it.
Returns the connection route on success or a concrete reason on failure.

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": "iphone_start_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the annotations with operational facts an agent cannot infer: expected latency of 10–90 s, that it works over cable or Wi-Fi, and the hard prerequisite that the iPhone must be unlocked. It also describes the failure surface – a locked device yields a result saying so and requires user action – which the idempotentHint and destructiveHint=false annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each carrying distinct and needed information: purpose plus prerequisite, trigger condition, re-entrancy and latency/hardware requirements, and outcome reporting. The prerequisite is front-loaded before the operational details.

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?

Despite returning a connection route via an output schema, the description still summarizes success and failure outcomes, and covers duration, transport, and the unlock precondition. For a zero-parameter prerequisite tool with annotations and an output schema present, nothing an agent needs in order 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?

The tool takes no parameters, so there is nothing for the description to disambiguate; schema coverage is reported at 100% with an empty properties object. Baseline for a zero-parameter tool applies.

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?

States a specific verb and resource ('Start WebDriverAgent on the iPhone and connect to it') and immediately declares its position in the tool graph as a prerequisite for all other iphone_* actions. That prerequisite framing alone distinguishes it from iphone_status and every other sibling.

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

Usage Guidelines5/5

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

Gives an explicit trigger: 'Call it when iphone_status or another tool reports no connection.' It also pre-empts the most likely agent hesitation by stating it is safe to call again because the operation is idempotent in practice, and it names iphone_status as the diagnostic that routes here.

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