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

No annotations are provided, so the description carries the full disclosure burden. 'Requires an active iOS automation session' reveals a prerequisite, and point-based coordinate usage is noted. However, it doesn't disclose side effects (e.g., whether it triggers navigation, momentum scrolling, or interaction with on-screen elements), possible failures (out-of-bounds coordinates), or default behavior with the duration parameter.

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 a single tight sentence that conveys purpose and coordinate semantics efficiently. It's appropriately brief with no filler. Slightly more behavioral detail could have been added without being verbose, but as written it's compact and to the point.

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 gesture tool with no annotations, no output schema, and six parameters, the description provides a minimal but functional picture. It covers the core action, coordinate units, and session prerequisite. However, it omits important context such as interplay with velocity/duration, whether swipes trigger accessibility events, and how it differs from ios_drag_drop or ios_scroll offerings. Adequate but leaves room for richer behavioral expectations.

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 100%, so all 6 parameters are documented in the schema. The description adds context about coordinate semantics (physical screen points) which helps interpret x1/y1/x2/y2 beyond mere 'Start/End coordinates.' However, it doesn't elaborate on the duration parameter's behavior or edge cases (e.g., relationship between speed and duration). Baseline 3 is appropriate since schema handles parameter documentation.

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?

Description states a specific verb (swipe) with clear from/to coordinates on an iOS device screen, and clarifies coordinates are in physical screen points. It distinguishes reasonably from siblings like device_swipe (non-iOS specific) and ios_swipe_hid (HID variant), though it doesn't explicitly call out those distinctions.

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 description notes 'Requires an active iOS automation session,' which implies session prerequisites, and mentions physical screen points vs coordinates. However, it doesn't differentiate from ios_swipe_hid, ios_tap, ios_drag_drop, or similar gesture tools, nor explain when to prefer swipe over scroll or drag. Context is implied but no alternatives are named.

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