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

No annotations are provided, so the description carries the full burden. It discloses that the polyline lands exactly as given, that points are ordered (first=touch-down, last=lift), that omitting 't' auto-spaces evenly and controls speed→momentum, and that a minimum of 2 points is required. It also states the prerequisite of an active iOS automation session. This is strong behavioral disclosure, though it doesn't elaborate on failure modes or what happens with an inactive session.

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 compact (two sentences) and front-loaded with the core purpose. Every sentence earns its place: the first establishes what the tool does and differentiates it, the second explains the parameter semantics and prerequisites. It's well-structured but slightly dense with technical detail that could arguably be trimmed without loss.

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?

The description is complete for a gesture tool with two well-documented parameters at 100% schema coverage. No output schema exists, but nothing about the return value is critical for invocation. Given the complexity of gesture timing, the description adequately covers the main considerations (ordering, timing, minimum points, session prerequisite) without needing to enumerate every edge case.

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 schema documents both parameters (udid, points) well. The description adds meaningful semantics: 'points' is described as an ordered list with {x, y, t?}, and crucially explains that 't' is ms from touch-down and that omitting it auto-spaces evenly AND controls speed→momentum. This adds behavioral meaning to the 't' parameter beyond the schema's 'Milliseconds from touch-down (optional)'.

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 clearly states the tool replays a freeform stroke as ONE continuous touch on an iOS device. It explicitly distinguishes itself from ios_swipe ('any gesture a straight ios_swipe cannot express'), lists concrete use cases (curves, arcs, signatures, unlock patterns), and names the sibling it differentiates from. Very specific verb+resource+scope.

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 explicitly tells when to use it ('curves, arcs, signatures, unlock patterns, or any gesture a straight ios_swipe cannot express') and implicitly defines when not to (straight gestures should use ios_swipe). It also documents the 't' omission behavior controlling speed/momentum — clear operational context for when to provide timing versus use defaults.

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