Safari MCP Server

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

No annotations are provided, placing full burden on the description. The text discloses nothing about behavioral traits: whether this triggers HTML5 drag events or mouse events, if it waits for element visibility, side effects on the browser state, or error handling when elements aren't found.

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?

Extremely efficient at two sentences. The first establishes purpose; the second addresses the dual input methodologies. No redundant words or filler content.

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?

Given six parameters with complex interdependencies (selectors vs coordinates) and no output schema, the description covers the bare minimum but leaves significant gaps. It lacks return value documentation, error scenarios, and explicit parameter relationship rules that would be expected for this complexity level.

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 coverage, baseline is 3. The description adds crucial semantic value by clarifying the 'or' relationship between selector-based and coordinate-based targeting, which is not explicit in the schema (where all 6 parameters are optional). This helps the agent understand valid parameter groupings.

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 core action ('Drag an element') and target ('another element or position'), distinguishing it from sibling interaction tools like safari_click or safari_hover. However, it omits the Safari/browser automation context that the tool name implies.

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?

While the description mentions the two input methods ('CSS selectors or x/y coordinates'), it fails to provide guidance on when to use this tool versus siblings (e.g., when to drag versus click), does not explain which parameter combinations are valid, and offers no prerequisites or error conditions.

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