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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does disclose the alias behavior (delete vs backspace, 'iOS soft keyboard treats both the same in most contexts'), the dropped-key-events behavior when keyboard isn't raised, and the session requirement. However, it doesn't disclose whether the press is synchronous vs asynchronous, whether it returns success/failure status, or any error conditions, which for a no-annotation tool leaves some gaps.

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?

Description is efficient—each sentence earns its place. It front-loads the core action, then categorizes button types, then provides the critical keyboard-raised caveat. No filler or redundancy. At roughly 60 words, it's appropriately sized for a tool with nuanced button semantics.

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?

Given the simple schema (2 simple params, no output schema, no annotations), the description covers the essential prerequisites (active session), the button semantics, and the critical timing caveat about keyboard visibility. The only notable gap is not describing what the tool returns or how to verify success, but for a press-action tool the risk is low and the description handles the important operational details well.

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 description coverage is 100% and both params (udid, button) are simple with self-describing names. The description adds value by explaining specific valid button values and their semantic meanings (e.g., delete is an alias for delete-right, tab is whitespace), which goes beyond the schema's bare list of button names. For a 2-param schema with full coverage, this is strong compensation.

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?

Description clearly states the action (press a button on iOS device) and enumerates specific button categories with exact names (home, volumeUp, volumeDown, return, go, done, search, backspace, delete, tab). It distinguishes between hardware, keyboard submit, and editing buttons, providing clear resource scope. The description differentiates this from sibling tools like ios_press_button_hid and device_key by specifying the semantic button names rather than HID codes.

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?

The description notes it 'Requires an active iOS automation session' and provides a critical usage caveat about the soft keyboard needing to be visibly raised before backspace. However, it doesn't explicitly state when to prefer this over siblings like ios_press_button_hid, ios_key_hid, or device_key, or mention scenarios where it should NOT be used (e.g., when HID-level control is needed).

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