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

With no annotations, the description carries the burden of behavioral disclosure. It covers coordinate frame ('same frame as ios_page_source'), single-contact limitation, and an error condition on unsupported platforms. However, it does not describe what a successful return value looks like or whether the tap is instantaneous or has any side effects, leaving a small gap.

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?

Three tightly written sentences, each serving a distinct purpose: action, coordinate context, and usage guidance including a fallback caveat. No redundant phrasing or unnecessary details.

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?

For a simple tap tool, the description is nearly complete: it explains what it does, when to use it, coordinate semantics, and a platform-specific failure case. The lack of explicit success return information is minor given no output schema and the trivial nature of a tap action.

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 100%, so the schema already documents parameter types and defaults. The description adds value by clarifying the coordinate reference frame ('iOS screen points (same frame as ios_page_source)'), which is not fully explained in the schema's x/y descriptions.

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 states a specific verb and resource: 'Tap at (x,y) via the direct input path'. It clearly distinguishes from sibling ios_tap by noting 'no automation session needed' and 'force HID', making its purpose unambiguous.

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?

Explicitly states when to use this tool vs alternatives: 'Prefer ios_tap for normal automation; use this to force HID or when the automation session is unavailable.' Also provides a critical environment caveat: 'Returns "no HID available" on iOS 17.x / no-tunnel.'

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