Tap

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

No annotations are provided, so the description carries the full burden. It discloses one behavioral modifier (stealth uses mobilerun-core's humanized tap), but says nothing about what a tap does as a side effect, whether it waits for the UI to settle, or whether it can fail/be retried. That is thin for an action tool with zero annotation coverage.

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?

A single sentence with the primary coordinate/mark behavior front-loaded and the stealth caveat trailing. Zero filler, though the parenthetical makes it slightly dense to parse.

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?

An output schema exists, so return values need no explanation. However, with 5 parameters, no annotations, no defaults documented, and an unexplained device param and x/y vs som_id precedence, the definition is only minimally complete for an action tool.

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 0% across 5 params, so the description must compensate. It adds real meaning for som_id (source tools) and stealth (humanized tap), and loosely covers x/y, but the device parameter and the x/y-with-som_id precedence rule are left entirely unexplained.

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: tap at (x, y) or at a numbered mark via som_id, and names the sibling tools that produce som_id (perceive_screen / read_screen). It implicitly distinguishes itself from double_tap, long_press, and tap_node by being the plain single tap, though it never says so explicitly.

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 tells the agent where som_id comes from and that stealth=true switches to a humanized tap, but gives no guidance on when to prefer this over the many siblings (double_tap, long_press, tap_text, tap_node, tap_and_wait) or what prerequisites exist. Usage is only implied.

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