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

Annotations only mark it as a non-read-only, non-destructive, non-idempotent mutation. The description goes well beyond that: it discloses single-contact-only behavior, the reason both dwell parameters exist, the norm-based coordinate mode, and a concrete failure mode ('no HID available' on iOS 17.x / no-tunnel).

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?

Front-loads the core action, then the swipe contrast, then use cases, then the normalization flag and the failure mode. Dense with parentheticals but each clause carries information; only the jigsaw/cards examples feel slightly expendable.

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 and 8 fully documented parameters, the description still covers the essential gaps an agent would hit: coordinate space, hold semantics, contact count, and the platform/tunnel failure case. Remaining omission is minor (no guidance on durationMs tuning or fallback when HID is unavailable).

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%, so the baseline is 3, but the description adds real meaning: the norm=true formula (pixelInScreenshot ÷ screenshotSize), why holdStartMs/holdEndMs matter (pick up the item vs. register the drop), and that waypoints live in the same coordinate space as from/to.

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+resource ('drag-and-drop via the direct input path') plus the operational distinction that no automation session is needed. It explicitly differentiates itself from the sibling ios_swipe_hid by contrasting hold behavior at both ends, so an agent can pick it without reading either schema.

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?

Gives concrete use cases (reordering, sliders, canvas drag-and-drop with jigsaw pieces/cards) and explains why it beats a bare swipe (grab/land failures). It does not mention when NOT to use it or name other drag-capable siblings such as ios_drag_drop or device_drag_drop, so alternatives are only partially routed.

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