Safari MCP Server

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

With no annotations provided, the description carries the full burden of behavioral disclosure, but offers minimal context. It fails to state whether emulation persists across page navigations, affects other tabs, requires specific permissions, or how to revert the changes (despite the existence of 'safari_reset_emulation').

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 in two sentences: the first establishes purpose and mechanism, while the second enumerates valid device values and the custom dimension alternative. Every sentence earns its place with no redundant filler.

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 100% schema coverage and 5 optional parameters, the description adequately covers the basic usage pattern. However, it lacks critical contextual gaps regarding persistence, scope of effect (tab vs. global), and relationship to the reset tool, which would be necessary for a mutation tool of this type without annotation support.

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 description coverage is 100%, establishing a baseline of 3. The description adds a few specific device examples (iphone-14-pro-max, ipad-pro) not listed in the schema's 'etc.' clause, but largely repeats information already present in the property descriptions without clarifying parameter precedence (e.g., if 'device' conflicts with 'width/height').

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 specific action ('Emulate a mobile device') and mechanism ('resizing window and setting user agent'). However, it does not explicitly differentiate from sibling tool 'safari_resize', which may also adjust viewport dimensions but presumably without changing the user agent.

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 no guidance on when to select this tool versus alternatives like 'safari_resize' (for simple viewport changes) or 'safari_reset_emulation' (to undo this action). It only describes parameter options (device presets vs. custom dimensions) without tool-selection heuristics.

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