swipe

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

No annotations are provided, so the description carries the full burden, and it does well: it discloses the short-swipe-becomes-tap behavior, the literal return value ('Swiped'), and that read_screen is needed to observe the effect. It omits any notes on failure cases or coordinate bounds, keeping it just short of a 5.

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 sentences, front-loaded with the core action, then usage, then return/follow-up. Every sentence carries distinct information with no filler.

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?

With no output schema, the description compensates by stating the return value ('Swiped') and the follow-up (read_screen). Coordinates, duration, edge cases, and alternatives are all covered, so nothing needed to invoke it correctly is missing.

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% and each parameter is already documented, including the duration_ms slow-drag/fast-fling semantics. The description reinforces the pixel coordinate meaning but adds no syntax or semantics beyond the schema, so baseline 3 is correct.

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 and resource — drag a finger from (x1,y1) to (x2,y2) in screen pixels — and positions it against siblings ('gestures scroll doesn't cover'), so an agent can differentiate it from scroll, tap, and long_press.

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?

Enumerates concrete when-to-use cases (slider, swipe a card/message aside, pull-to-refresh, map drag) and adds the edge case that a very short swipe counts as a tap, implicitly routing toward tap. Explicit context and exclusions are present.

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