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. It explains the mechanism (CGEvent), side effects (physical mouse movement, window visibility requirement), and security implications (isTrusted events). It does not mention error handling or failure modes, preventing a perfect score.

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?

Five sentences, each serving a distinct purpose: mechanism/benefit, error-condition usage, trade-offs, parameter options, and prerequisites. No redundancy or filler. Information is front-loaded with the OS-level nature of the tool.

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 the complexity of OS-level automation and lack of annotations, the description comprehensively covers mechanism, use cases, limitations, and parameter relationships. It lacks only output/error specification, which is acceptable given the tool's action-oriented nature and absence of output schema.

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?

While schema coverage is 100% (baseline 3), the description adds crucial semantic context: it clarifies that ref, selector, text, and x/y are alternative targeting methods ('Use ref... selector, text, or x/y') and provides operational guidance that ref requires a 'FRESH safari_snapshot'—critical information not present in 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?

The description explicitly states the tool performs 'OS-level mouse click via macOS CGEvent' and clearly distinguishes it from the sibling 'safari_click' by explaining it produces 'isTrusted: true events' that bypass WAF/bot detection. Specific mechanism (CGEvent) and benefit (passing Cloudflare/G2) are included.

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 explicit when-to-use guidance: 'Use when regular safari_click fails with 405/403 errors or form submissions are blocked.' Also details critical trade-offs ('physically moves the mouse cursor and requires Safari window to be visible') and prerequisites ('When using ref, always take a FRESH safari_snapshot first').

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