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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false), and the description adds genuinely useful context: no automation session is needed, the contact persists until ios_release_hid, and it returns 'no HID available' on iOS 17.x / no-tunnel. That error/environment disclosure goes beyond the annotations.

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-loads the core action and lifecycle, then tacks on the coordinate and error notes. Dense but every clause carries information; no wasted preamble.

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 mutation/input primitive with annotations and a named release companion, the description covers what the operation does, how long it persists, and a failure mode. No output schema exists, but the return-value note ('no HID available') is supplied anyway, leaving little missing.

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 x, y, norm, and udid are already documented. The description repeats the coordinate-space fact ('Coordinates are iOS screen points'), which is baseline value and slightly understates the norm=true fraction mode the schema describes.

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 a single contact at (x,y) via direct HID — and explicitly notes it stays held without lifting. An agent can distinguish this from ios_tap and ios_contacts_hid directly from the description.

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?

Names the use case ('hold-then-steer interactions the automation session cannot express') and the lifecycle pairing (held until ios_release_hid), which routes the agent correctly. It stops short of explicit when-not-to-use or differentiating from ios_contacts_hid by name.

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