Skip to main content
Glama

iphone_tap_text

Tap a visible iPhone element by its label text instead of screen coordinates: locates buttons, cells and links by visible text alone, so a tap does not depend on layout or screen size.

Instructions

Find a visible element by its text and tap its center.

Prefer this over iphone_tap for buttons, cells and links with a label: it does not depend on layout or
screen size. If nothing matches, it says so and taps nothing; with several matches it reports how many
there are so you can pick another with `index`. Like a finger tap, the effect depends on the element.

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": {
      "text": "<text>"
    },
    "name": "iphone_tap_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesVisible text of the element to tap, matched case-insensitively against its label, name and value.
exactNotrue requires the whole label to equal the text instead of containing it.
indexNoWhich match to tap when several elements match, 0 = topmost on screen.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.2.0
    • addedInput schema / properties / exact / description
      Added value: +"true requires the whole label to equal the text instead of containing it."
    • addedInput schema / properties / index / description
      Added value: +"Which match to tap when several elements match, 0 = topmost on screen."
    • addedInput schema / properties / index / minimum
      Added value: +0
    • addedInput schema / properties / text / description
      Added value: +"Visible text of the element to tap, matched case-insensitively against its label, name and value."
    • addedInput schema / properties / text / minLength
      Added value: +1
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations only declare the generic profile (not read-only, open-world, non-idempotent, non-destructive). The description adds real behavioral detail beyond that: a no-match case is a no-op that reports the failure, multiple matches report a count so the agent can retry with `index`, and the outcome depends on the tapped element. It stops short of describing timing/visibility settling or what the response payload looks like, though an output schema exists to cover the latter.

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?

Three tight sentences, front-loaded with the action, then the sibling preference, then the edge cases. No filler or redundancy.

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 the action, the alternative tool, the failure mode, the ambiguity handling, and outcome uncertainty. With an output schema present, return values need not be described, so what remains is exactly the guidance an agent needs to call this correctly.

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 100%, so the baseline is 3. The description still earns credit by explaining the workflow behind `index` (used to pick among several reported matches), tying the parameter to a concrete decision rather than restating the schema.

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+resource: 'Find a visible element by its text and tap its center.' It is immediately distinguishable from the sibling iphone_tap (coordinate-based), which it names explicitly.

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 routing rule: prefer this over iphone_tap for buttons, cells and links with a label, with the reason (no dependence on layout or screen size). It also tells the agent what to do when several matches occur (use `index`), which is a secondary selection workflow.

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