safari_native_hover

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals key traits: moves the real cursor, triggers native events, dwells for `dwellMs`, and restores cursor by default. However, it does not mention potential side effects, permission requirements, or error handling for missing elements.

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 efficiently structured: it opens with the core action and mechanism, then provides use cases, follow-up steps, default behaviors, and prerequisites. Every sentence adds value, and no superfluous information is present.

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?

Despite lacking an output schema, the description adequately covers key aspects: element targeting, dwell timing, cursor restoration, and the need for subsequent reading. It could be more complete by covering error scenarios, but given the tool's specialization and 7 parameters, it provides sufficient contextual completeness.

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?

The input schema has 100% description coverage, providing baseline semantics. The description does not significantly add meaning beyond the schema; it mentions targeting via `selector`, `text`, `x`, `y`, but does not clarify how these alternative methods work together or in relation to `ref`. The baseline of 3 is appropriate.

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 identifies the tool as performing an OS-level mouse hover via macOS CGEvent, specifying the verb, resource, and mechanism. It distinguishes itself from the sibling tool `safari_hover` by highlighting its ability to trigger native `:hover`/`mouseenter` handlers, which JS-dispatched events cannot.

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 provides explicit usage scenarios (obfuscated UIs like Discord server sidebars, portal-rendered tooltips) and follow-up actions (call `safari_wait_for` or `safari_evaluate`). It also notes prerequisites (Safari window visible) and default behavior (cursor restoration), offering clear guidance on when and how to use this tool vs alternatives.

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