aua_drag

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the mutating, non-deterministic nature is known. The description adds useful context that this is a single gesture with no automatic replay and that coordinates are in Android display pixels. It does not disclose what the gesture may trigger, whether it blocks, or what the observe options return.

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?

Three short sentences with the core gesture and coordinate units front-loaded; nothing is padded. The trailing "No automatic replay" sentence is terse enough to be terse-but-earned rather than wasteful.

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 6-parameter gesture tool with zero schema description coverage and no output schema, the description leaves too much unexplained: the relationship between observation_id and aua_observe, the semantics of the duration bound, and the behavior of the observe/wait_for options are all missing. It is enough to attempt a call but not enough to call it correctly in a real workflow.

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%, so the schema supplies types and bounds but no meaning. The description contributes the genuinely useful unit clarification (Android display pixels for start/end) and names duration, observation_id, wait_for, and observe, but does not explain what duration controls (press-hold timing), what observation_id must reference, or how wait_for gates the call.

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?

"Drag once from start {x,y} to end {x,y}" gives a specific verb and resource plus the coordinate shape, so the action is unambiguous. It does not distinguish itself from similar gesture siblings such as aua_swipe or aua_long_press, which is the only real gap.

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?

There is no guidance on when to choose a drag over aua_swipe, aua_long_press, or aua_scroll_until, nor any stated prerequisites such as needing a prior observation. "No automatic replay" hints at the execution model but is a behavior note rather than when-to-use guidance.

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