aua_scroll_until

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

Annotations only declare readOnlyHint=false, openWorldHint=true and idempotentHint=false; the description adds substantive behavior beyond that, including the max_swipes/timeout_seconds bounds, the early-stop rules (two unchanged regional snapshots, app/display change), and the fact that no_progress is not proof of list end. It does not say what is returned or raised when the selector is never found, which is the main remaining behavioral gap.

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 description is dense and front-loaded: purpose first, then bounds, then stop conditions, then caveats. Nothing is redundant, though the telegraphic phrasing ("no_progress does not prove list end") is terse enough to require interpretation and references a term never defined in the schema.

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?

This is a complex mobile-automation tool with 8 undocumented parameters and no output schema, so the description should do more. It adequately covers termination behavior and region usage, but leaves most parameter semantics, the direction default, and the failure/return shape 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 description coverage is 0% across 8 parameters, so the description must carry parameter meaning, yet it only touches max_swipes, timeout_seconds and region. It says nothing about selector (the sole required parameter, with many fields like text_contains, index, clickable), observe, duration or settle_seconds, and it silently ignores that direction defaults to "up" — a non-obvious default an agent could easily get wrong.

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 gives a precise verb+resource combination (find a visible selector, swiping only when it is absent) and clarifies the mechanism that separates it from a plain swipe or find tool. It does not name the sibling alternatives (aua_find, aua_swipe) that an agent would otherwise have to guess between, so it falls short of a 5.

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 states key usage conditions: swipe only if the selector is absent, use region for nested lists, and the result is not clicked (so a follow-up tap is needed). It also warns that no_progress does not prove list end. What is missing is an explicit alternative routing (e.g. use aua_find when the element is already on screen), so the exclusions remain implied.

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