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

Annotations already declare destructive=true, openWorld=true and non-idempotent, so the safety profile is covered. The description adds real behavioral context the annotations cannot: the call blocks until the screen settles, a no-change result is a probable miss, and read actions (installed/notifications/clipboard/app_info/crashes/health) do not touch the UI. It does not discuss permissions or what a destructive action can actually break.

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?

One dense paragraph covering failure handling, input preference, and a full read-action list. The read-action enumeration and the action names largely duplicate the `action` and `text` schema descriptions, so several clauses do not earn their place; no structure is used to separate routing advice from action documentation.

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 21-action dispatcher with 10 parameters, the description covers the critical unknowns: blocking/settle behavior, failure interpretation, focus requirement for typing, and the read-only action subset. An output schema exists, so return values need not be explained, and defaults for ms/timeout are handled by the schema.

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 every parameter, including the per-action `text` mapping and coordinate meanings. The description adds only marginal extra meaning, chiefly that `tap_text` matches elements whose text *contains* the string (substring, not exact) and that `element` comes from the last `observe`. Baseline 3 applies when the schema carries the detail.

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 opening sentence is vague ("Do one thing on the phone yourself"), but the body makes the scope concrete: a single device action drawn from a named action set, plus read-only variants. It distinguishes itself from siblings explicitly, telling the agent to use `observe` for element numbers and `run` for a whole goal.

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 explicit routing rules: prefer `element` from the last `observe` over raw coordinates, use `run` when the task is a multi-step goal, and re-`observe` when the screen did not change. It also states a prerequisite ordering for typing (tap the field first).

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