Safari MCP Server

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

No annotations provided, so description carries full burden. Discloses output format ('accessibility tree', 'structured text'), performance characteristics ('cheaper', 'heavy image' for alternative), and integration pattern (refs for click/fill/type). Lacks explicit statement on whether operation is read-only/safe.

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?

Six information-dense sentences with zero waste. Front-loaded with preference statement, followed by technical details, workflow example, comparative analysis, and exclusion guidance. Excellent pacing and structure.

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?

Compensates effectively for missing output schema by detailing return structure ('accessibility tree with ref IDs') and demonstrating consumption pattern with other tools. Complete for standard use cases, though error conditions or edge cases (empty page, no interactive elements) are not addressed.

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?

Input schema has 100% description coverage for the 'selector' parameter. Description provides no additional parameter details, but with full schema coverage, baseline 3 is appropriate as no compensation is needed.

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?

States specific action ('Returns accessibility tree with ref IDs') and resource scope ('every interactive element'). Explicitly positions itself as the 'PREFERRED way to see page state' and distinguishes from siblings safari_screenshot and safari_read_page by contrasting output formats and cost.

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 workflow ('snapshot → see refs → click'), direct comparisons ('PREFER THIS over safari_screenshot... and over safari_read_page'), and clear exclusion criteria ('Use safari_screenshot only when you need to see visual layout/styling').

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