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

With no annotations provided, the description carries full responsibility. It discloses that no automation session is needed, the hold persists until ios_release_hid is called, coordinates are iOS screen points, and it returns an error on iOS 17.x/no-tunnel. These are key behavioral traits that are not inferable from the schema or 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?

The description is three sentences, front-loaded with the core action and the critical 'without lifting' qualifier, then adds the release dependency and error condition. No wasted words; every sentence provides value.

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 hold action with no output schema, it covers the main requirements: how to invoke, the held state, the release counterpart, coordinate system, and error case. It omits minor details like behavior if the device is already in a held state, but these are edge cases not essential for typical usage.

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 all parameters including norm and coordinate format. The description adds minimal extra meaning beyond restating that coordinates are screen points; it does not clarify the norm option's interaction or any edge cases. Baseline 3 is appropriate.

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 clearly states a specific action: press-and-hold a single contact at coordinates via direct HID input, and explicitly contrasts with alternatives by noting it does not lift. The phrase 'without lifting — mouse-button-down / touch-down' precisely defines the behavior, and the reference to 'hold-then-steer interactions' differentiates it from tap or timed-press tools.

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?

It provides a specific use case ('hold-then-steer interactions the automation session cannot express') and mentions the companion tool ios_release_hid, but it does not explicitly name sibling tools like ios_tap_hid or ios_long_press_hid. Still, the guidance is clear enough for an agent to know when to invoke it.

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