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

Adds meaningful behavioral context beyond annotations: direct HID input without a session, persistent held state across calls, frame semantics, and the specific failure mode on iOS 17.x / no-tunnel. This is valuable state and error disclosure for a stateful input tool.

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?

Front-loaded with the core action, then immediately explains frame behavior, held state, coordinate system, and error behavior. Every sentence carries useful information with no padding.

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 stateful HID input tool with rich schema coverage and no output schema, the description covers the essential behavioral contract: multi-finger hold, repeated calls for steering, release requirement, coordinate space, and platform failure condition.

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%, so the schema already documents udid, points, ordering, and norm semantics. The description adds only that coordinates are iOS screen points, which is already covered by the norm parameter documentation.

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?

States a specific verb and resource: press-and-hold up to five contacts via direct HID input without lifting. It distinguishes itself from single-contact and release siblings by naming the release tool and explaining the multi-finger held-state behavior.

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?

Clearly explains how to use it: one call is one frame, call repeatedly to steer, fingers stay held until ios_release_contacts_hid. It also notes no automation session is needed, but does not explicitly compare against alternatives such as ios_contact_hid or non-HID multi-touch tools.

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