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

No annotations exist, so the description carries the full burden. It does disclose the key behavioral fact that this is a mutating interaction whose result is the next screen, but it omits whether refs expire after use, what happens on an invalid ref, or whether the tap can trigger destructive app-level actions.

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?

Two short sentences, zero redundancy, and the action and its outcome are front-loaded. Nothing could be cut without losing information.

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 two-parameter tool with no annotations and no output schema, the description covers the essential contract: what it acts on and that the response is the new screen. Remaining gaps (ref lifecycle, error behavior) are moderate rather than fatal.

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 both parameters (ref with pattern and example, session sourced from open_app) are already fully documented. The description only echoes the 'by ref' concept without adding format or lifecycle details, which is the baseline 3 case.

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 (tap) and the target resource (button, link or choice by ref), plus the observable result (returns the new screen). This is clearly distinguishable from siblings like scroll, type and back, though the description doesn't explicitly name those boundaries.

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?

Usage is only implied: tap an interactive element by ref. There is no statement of prerequisites (a live session, a ref from a prior screen call), no failure behavior for stale refs, and no routing to alternatives such as scroll or back when an element isn't visible.

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