phone_tap

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

With no annotations, the description still discloses the experimental status, the runtime prerequisites, and the specific error surface ('refused with mirror_not_live when the mirror is paused'), which is the kind of mutation-safety context an agent needs. It stops short of describing what a successful tap returns or any confirmation side-effects.

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?

Four short sentences, front-loaded with the experimental warning, and every clause carries information an agent needs (warning, prerequisites, coordinate convention, failure mode).

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 two-axis pointer tool with no output schema, the description covers the critical unknowns: environment dependency, coordinate convention, and the primary failure mode. Only the coordinate origin and post-tap verification are unaddressed.

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 0% and both parameters are undocumented there, so the description must carry the load; it does add the key fact that coordinates are normalized 0-1, but it omits the origin corner and the fact that both are optional per the schema.

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-resource pair ('Tap at {x, y}') and anchors it to iPhone Mirroring, so an agent can tell it apart from mac_click and phone_scroll without opening the schema.

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 gives prerequisites ('Needs iPhone Mirroring and a python3 with pyobjc') and a refusal condition, but never says when to prefer this over phone_find, phone_longpress, or mac_click, nor what to do instead when the mirror is paused.

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