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 of behavioral disclosure. While 'Get' implies a read-only operation, the description does not explicitly confirm it is non-destructive, does not indicate whether it waits for page load completion (necessary for accurate Web Vitals), or describe the return format/structure.

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 a single, efficiently structured sentence that front-loads the action ('Get detailed performance metrics') followed by a colon-separated list of specific metric types. There is no redundant or wasted text.

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 absence of an output schema, the description partially compensates by listing the specific metric categories returned. However, it lacks information about the data structure, units, or timing requirements (e.g., whether metrics are cumulative or point-in-time), leaving gaps in contextual completeness.

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?

The input schema contains zero parameters. Per evaluation rules, tools with no parameters receive a baseline score of 4, as there are no parameter semantics to describe beyond the schema itself.

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 it retrieves 'detailed performance metrics' and specifically enumerates the metric categories covered (navigation timing, Web Vitals with specific acronyms FCP/LCP/CLS, resource breakdown, memory usage). This distinguishes it from sibling tools like safari_network or safari_css_coverage by focusing on Web Vitals and timing data.

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 use this tool versus alternatives like safari_network (which captures network traffic) or safari_analyze_page. It does not mention prerequisites such as requiring a page to be loaded first, or whether it should be called before/after specific actions.

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