swipe

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

With no annotations, the description carries the full behavioral burden. It discloses what the gesture does (page flip, dismiss, drag, zoom), which is meaningful context, but says nothing about coordinate format, gesture duration/velocity, whether a dismiss is irreversible, or what the call returns on success/failure. It covers the semantic layer while leaving the operational layer implicit.

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 clauses, each earning its place: gesture purpose, parameter semantics, and the sibling routing note. The parameter explanation is front-loaded before the alternative, with zero 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?

For a 4-parameter, zero-required, annotation-free UI automation tool with no output schema, the definition is workable but thin: it never states what the tool returns or how a swipe is confirmed, and it leaves the `direction` parameter's role relative to `to`/`from` ambiguous. An agent could call it, but might need trial and error on the parameter combinations.

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 50%, so the description must compensate, and it does: it explains that `to` drags `from` to a target and that `pinch` takes in/out values, meaning the agent learns the drag pairing and the pinch vocabulary. `direction` is left to the schema's enum list, and interaction between `direction` and `to`/`from` is unaddressed, keeping it below 5.

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 states a concrete verb+resource ('A finger gesture') and enumerates the gesture outcomes: flip pages, dismiss, drag, pinch zoom. It also names the sibling it differs from ('Use `scroll` for lists'), so an agent can separate swipe from scroll. It stops just short of 5 because the gesture taxonomy (drag vs pinch vs directional flick) is only loosely mapped to the parameters.

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 gives one explicit routing rule — use `scroll` for lists — which is exactly the kind of alternative-selection guidance that matters here. It does not state when-not to swipe (e.g., on elements that need tap, or when a fling would overshoot), so the guidance is clear but not exhaustive.

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