Skip to main content
Glama
Sign In
iphone-use

iphone-use

by leeguooooo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

phone_subtree

Read-only

Read a single native element's bounded subtree by snapshot and element, avoiding a full app-tree walk. Use returned rows only for inspection; complete=false may mean missing descendants.

Instructions

Read one native element's bounded subtree by element+snapshot, serializing only that element (locator lookup may still read the app tree). Requires a unique live semantic target and a runner with ipu:elementSubtree. Returned row positions are READ ONLY, not action refs; use unique locators or fresh phone_elements refs for input. complete=false means descendants may be missing.

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": {
      "snapshot": "<snapshot>",
      "element": "<element>"
    },
    "name": "phone_subtree"
  }
}

Input Schema

NameRequiredDescriptionDefault
elementYes
instanceNoInstalled local instance name, such as i13 or default. Omit to use the configured daemon. No fallback on failure.
snapshotYes
max_depthNoRelative depth cap (1..64), default 8.
max_nodesNoNode cap (1..5000), default 500.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.28.1

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: discloses that locator lookup may still read the app tree, that a specific runner capability is needed, that complete=false signals missing descendants, and that returned row positions are READ ONLY and not valid action refs. These are exactly the failure modes an agent would otherwise trip over.

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-loads what is read before the caveats, and every sentence carries a distinct constraint. It is dense with jargon ('ipu:elementSubtree', 'fresh refs') but no sentence is filler.

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?

With no output schema, the description still covers the key return semantics (only the selected element serialized, positional rows not actionable, complete flag). It stops short of describing the actual row shape, which is the main remaining gap for a read tool.

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?

Schema coverage is 60% with element and snapshot undocumented, and the description compensates by tying them together ('by element+snapshot') and requiring the element be a unique live semantic target. Depth/node caps are already documented in the schema, so no additional credit is warranted there.

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 (read) + resource (one native element's bounded subtree) + scoping keys (element+snapshot), and explicitly contrasts with a global tree walk / phone_elements full-tree reads, so an agent can distinguish it from the sibling listing tools.

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?

Gives prerequisites ('requires a unique live semantic target and a runner with ipu:elementSubtree') and a routing rule for follow-up input ('use unique locators or fresh phone_elements refs'). It does not explicitly say when to prefer this over phone_elements / phone_tap_element, so exclusion guidance is implied rather than stated.

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