auto_test

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

With no annotations, the description carries the full burden, and it does a lot: it discloses the data-variant strategy, scrolling-to-reach behavior, alert dismissal, the categories of problems reported, and that screenshots are captured. What it omits is similarly important for planning: whether the tool mutates or persists app state/data with all those taps, and roughly how long a run takes given up to 8 rounds of 100 steps.

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 core capability is front-loaded in the first clause, followed by a tight enumeration, then the usage directive. The single long sentence is dense and slightly run-on, but nearly every clause conveys distinct, actionable 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-optional-parameter tool with no output schema and no annotations, the definition covers what the tool does, what it produces (crashes, console errors, layout issues, dead buttons, screenshots), and the expected workflow. The remaining gap is operational: no sense of runtime cost or side effects on app data, which matters for a tool that taps everything up to 8 times.

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 100%, with both optional parameters documented including defaults (4 rounds, 30 taps) and min/max bounds. The description's mention of reloading 'several times' loosely maps to rounds but adds no syntax or trade-off guidance (e.g., when to raise rounds vs maxStepsPerRound), so the schema does the work and the baseline 3 applies.

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 opens with a specific verb+resource ('Automatically exercises the whole app') and then enumerates the concrete actions taken (reloads, fills TextInputs, taps buttons, dismisses alerts) and the outputs produced. This clearly distinguishes it from the sibling primitives like click_screen, type_text, and scroll_screen, which perform single steps rather than an end-to-end sweep.

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?

'Run it after every change, then fix what it reports and run it again' gives explicit timing and a follow-up loop, which is stronger than most tools provide. It stops short of stating when NOT to use it or naming a sibling alternative (e.g., manual click_screen exploration), so it earns a 4 rather than a 5.

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