safari_native_keyboard

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

Discloses key behavioral traits: produces isTrusted:true events, runs entirely in background, never activates Safari. Since no annotations are provided, the description adequately covers safety and side effects, though could mention if the keypress reliably triggers page interactions.

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?

Concise and well-structured: opening sentence defines purpose, second gives usage guidance, then enumerates keys and modifiers, followed by behavioral traits. No wasted words.

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?

Covers purpose, usage, parameters, and key behavioral effects. No output schema, so return value is not described, but for a simple keypress tool this is acceptable. Minor gaps like edge cases or potential failures are not addressed.

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 has 100% description coverage, and the description expands on valid keys and modifiers with explicit lists and examples, adding value beyond the schema.

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?

Clearly states it sends OS-level keyboard events via CGEvent to Safari without activating it or stealing focus. Distinguishes itself from safari_press_key by specifying it bypasses JS trust-gated handlers.

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?

Explicitly advises using this tool when safari_press_key fails for React trust-gated handlers (e.g., Discord, Slack). Provides examples but does not explicitly list when not to use it, or contrast with other sibling tools like safari_native_type.

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