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

With no annotations, the description carries the full burden. It discloses the key behavior: the contact stays held until ios_release_hid, and it returns an error message on unsupported environments. However, it states 'Coordinates are iOS screen points' without acknowledging the norm parameter, which slightly over-simplifies the coordinate behavior but does not contradict the schema.

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?

The description is concise (three sentences) with the action front-loaded. Every sentence earns its place: the behavior, the use case, coordinate context, and an error condition. No fluff or redundancy.

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 moderate complexity and lack of output schema, the description covers the essential context: the hold-then-steer interaction pattern, the need for ios_release_hid, coordinate system, and a failure condition. It does not describe a success return value, but that is often not critical for such a tool, and the description is sufficiently complete for an agent to use it correctly.

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 baseline is 3. The description does not add meaningful parameter-level information beyond the schema; it reiterates 'Coordinates are iOS screen points' and mentions the return error, which is not parameter-related. The schema already fully explains x, y, norm, and udid, so the description adds minimal value here.

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 starts with a specific verb-action 'Press-and-HOLD a single contact down at (x,y) via direct HID input ... WITHOUT lifting', clearly stating what the tool does. It distinguishes itself from sibling tools like ios_tap_hid or ios_long_press_hid by emphasizing the hold-without-release behavior and the need to pair with ios_release_hid.

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 explicitly states the intended use case: 'Use for hold-then-steer interactions the automation session cannot express.' It also notes 'no automation session needed', clarifying when this tool is appropriate, and mentions the complementary tool ios_release_hid. The error context ('iOS 17.x / no-tunnel') effectively warns when not to use it.

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