ios-mcp

Overview Schema Source Related Servers Discussions Admin

ios_type

Destructive

Type text into an iOS app field by ref or target, optionally clearing it or pressing return. Reads the field back to confirm input landed, failing if text was not entered.

Instructions

Type into a field, focusing it first when a ref or target is given.

The field is read back afterwards. If the text did not land, the call fails with typed.shown saying what the field holds; reformatted means it landed with the app's own capitalisation or formatting.

Input Schema

TableJSON Schema

Name	Required	Description
`ref`	No	A ref from the last observation, such as 'e7'. Preferred.
`text`	Yes	Text to type. Never a password; see ios_type_secret.
`submit`	No	Press return afterwards.
`target`	No	Plain description of the element, e.g. 'the Send button'. Used if no ref.
`approve`	No	Signature returned by a previous action_requires_approval error.
`idem_key`	No	Optional key making a retry a no-op. Pass the same key when repeating an action you are unsure completed.
`clear_first`	No	Replace the field's contents.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 1, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Adds real behavioral context beyond annotations: the field is read back after typing, a failure surfaces typed.shown with the actual field content, and 'reformatted' signals app-side capitalization. That is valuable post-condition disclosure absent from the structured hints, though it does not address the destructive clear_first behavior or the approval pathway.

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 short sentences, front-loaded with the core action, then verification behavior, then failure semantics. No filler and every sentence carries information.

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?

An output schema exists so return-value explanation is unnecessary, and the description usefully covers verification and error-signal semantics. It leaves gaps around the approval flow and destructive clear_first behavior for an openWorld, destructive, non-idempotent tool, but is otherwise solid.

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 100%, so all seven parameters are already documented with descriptions, making the baseline 3 appropriate. The description only echoes the ref/target focusing nuance already implied by the schema's 'Preferred' and 'Used if no ref' notes.

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?

States a specific verb and resource ('Type into a field') plus the focusing behavior when a ref or target is supplied. It is clear what the tool does, but it does not distinguish itself from close siblings like ios_set_value or ios_type_secret, which the agent must choose between.

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

Usage Guidelines3/5

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

Implies usage context by explaining that focusing happens when a ref or target is given, and implies these two selectors are alternatives. However, it never states when to prefer this over ios_set_value, when to use ios_type_secret, or any prerequisite for approval.

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