Safari MCP Server

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

No annotations are provided, so the description carries the full burden. While it mentions modifier support, it fails to disclose critical behavioral traits: which element receives the keypress (focused element?), whether default browser actions are triggered, or if the operation is synchronous.

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 optimally concise with two efficient sentences. The first covers the primary action and key examples; the second addresses modifiers. No redundant or filler text 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?

For a two-parameter tool without annotations or output schema, the description meets minimum viability by explaining the core function. However, it lacks necessary behavioral context (focus/target element behavior) that would be required for an agent to predict side effects or failure modes.

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?

With 100% schema description coverage, the baseline is 3. The description restates the modifier keys and provides examples of key names, which largely duplicates the schema documentation without adding significant semantic context about parameter interactions or formats.

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 action ('Press a keyboard key') and resource, with specific examples (enter, tab, escape, arrows) that implicitly distinguish it from the sibling 'safari_type_text' tool. However, it doesn't explicitly clarify the distinction between single key presses versus text input.

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 implied usage guidance through examples (navigation keys like arrows, functional keys like escape), suggesting use for keyboard navigation and shortcuts. However, it lacks explicit 'when to use' guidance or contrasts with alternatives like 'safari_type_text'.

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