Safari MCP Server

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

With no annotations, description carries full burden and discloses implementation details (React Fiber fallback, event sequence) and purity ('never touches user's mouse'). Does not describe post-click behavior or return values (though no output schema exists).

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?

Four sentences with zero waste: purpose → targeting options → technical mechanism → critical warning about ref freshness. Every clause earns its place.

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?

Complete for a DOM interaction tool given 100% schema coverage and no output schema. Minor gap: does not explicitly note that at least one targeting parameter must be provided (though implied by the 'Use... or...' construction).

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 coverage is 100% (baseline 3). Description adds crucial semantic context that 'ref' comes 'from snapshot' and the lifecycle constraint that refs expire after each snapshot, which is not evident from the schema alone.

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?

Description opens with 'Click element' (specific verb + resource) and distinguishes from siblings like safari_native_click by stating 'Pure JS — never touches user's mouse' and detailing the PointerEvent+MouseEvent+React Fiber mechanism that enables clicking on virtual DOM apps.

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?

Provides critical constraint 'When using ref, always take a FRESH safari_snapshot first — refs expire after each new snapshot' and lists targeting alternatives. Lacks explicit comparison to safari_click_and_read or safari_click_and_wait for when to use the base version.

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