Launches a URL or deep link—custom scheme or universal link—on a connected iPhone or iPad for app testing.
Open a URL or deep link (custom scheme or universal link) on the device.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| device | No | Device UDID or name substring. Defaults to the select_device choice, then IOS_DEVICE_MCP_DEVICE, else the single USB-connected device. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does add that custom schemes and universal links are supported, which is useful behavioral context, but it says nothing about mutating side effects, what happens on an invalid or unhandled URL, whether a session must be running, or what is returned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler; the parenthetical adds real information rather than padding. Nothing could be removed without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations and no output schema, the description should cover prerequisites and outcome behavior for a side-effecting device action, but it does not. An agent cannot tell whether it needs a driver session, what constitutes failure, or what the call returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50%: the 'device' parameter is well documented in the schema with a clear default-resolution chain, while 'url' has no schema description. The description compensates partly by defining url as a URL or deep link with custom-scheme/universal-link forms, but offers no format, encoding, or validation guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource ('Open a URL or deep link') and clarifies the accepted forms (custom scheme or universal link), which genuinely distinguishes it from launch_app. It stops short of explicitly contrasting itself with the app-launch sibling, but an agent can infer the difference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this instead of launch_app or tap (e.g., to trigger a deep link into an installed app), nor any prerequisites such as the device being booted or a driver session being active. Usage is only implied by the verb.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.