phone_scroll

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

With no annotations, the description carries the full burden and does reasonably well: it discloses experimental status, external runtime dependencies, the underlying mechanism (trackpad-style scroll events), and a concrete default of 0.5 window heights. It omits failure behavior and return values, but for a non-destructive scroll action the disclosed surface is substantially above bare minimum.

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 sentences, no filler, and the most decision-relevant facts (EXPERIMENTAL, prerequisites) are front-loaded before the action description. Every clause carries information an agent needs.

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 two-optional-parameter tool with no annotations and no output schema, the description covers environment requirements, semantics of the primary parameter, and the default. The remaining gap is the undocumented direction value set, which is the one thing that could cause a failed call.

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 0%, so the description must compensate. It explains `distance` well (units = window heights, default 0.5) but says nothing about the accepted values of `direction` beyond 'up or down' in prose, and the schema declares it as an unconstrained string with no enum — an agent cannot know whether 'up'/'down', 'Up'/'Down', or something else is expected.

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: scroll the list under the iPhone mirror by a distance in window heights, using trackpad-style events. This is clearly distinct from mac_scroll and browser_scroll through the 'under the mirror' scoping, though it never explicitly contrasts itself with phone_swipe, the closest sibling.

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 useful preconditions (iPhone Mirroring must be active, python3 with pyobjc installed, EXPERIMENTAL flag) which implicitly tells the agent when the tool is usable. It does not say when to prefer this over phone_swipe or mac_scroll, nor what to do when the prerequisites are unmet.

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