adb_swipe

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

With no annotations, the description carries the full burden. It does disclose one real behavioral trait — that duration_ms changes the gesture semantics (long press when start=end) — which is valuable. But it says nothing about whether the call blocks until the gesture completes, what permissions/device state are required, or what it returns.

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 with zero filler; the core action is front-loaded and the long-press tip follows immediately. Every sentence earns its place.

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?

No output schema and no annotations, with 6 parameters at 33% coverage — the description should do more. Coordinate units, blocking behavior, and the default-device fallback (only covered by the schema's device field) are the notable omissions for a gesture tool.

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 only 33%: device and duration_ms are documented, but x1/y1/x2/y2 have no schema descriptions. The description partially compensates by framing them as 'from one point to another' and by explaining the duration effect, but it never states the coordinate units (pixels vs. screen fractions), which is the single most consequential ambiguity for this tool.

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 (swipe) and the resource/scope (between two points), so an agent immediately knows the gesture it performs. However, it never distinguishes itself from siblings like adb_tap or adb_scroll, leaving the agent to infer the boundary between a swipe and a scroll gesture.

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?

The second sentence is genuinely useful usage guidance — it tells the agent how to achieve a long press with this same tool, which is a non-obvious invocation pattern. But there is no explicit statement of when to prefer adb_swipe over adb_tap or adb_scroll, and no exclusions or prerequisites.

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