Safari MCP Server

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

Without annotations, the description carries the burden of disclosing behavior. It partially compensates for the missing output schema by listing return fields (tag, text, rect, attributes, visibility), but fails to declare safety properties (read-only status), error handling (e.g., selector not found), or side effects.

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?

Extremely efficient single-sentence structure. The parenthetical list of return fields is precisely what an agent needs to evaluate utility. No redundant or filler 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?

For a single-parameter tool, the description adequately covers the output structure by listing fields, but lacks critical context regarding error states, safety classification, and differentiation from similar element-inspection siblings. Adequate but clear gaps remain.

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?

With 100% schema description coverage ('CSS selector'), the baseline is established. The description adds no additional semantics about the selector parameter (e.g., syntax limitations, scope), focusing instead on return value documentation.

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?

Clearly states the action (Get) and target (element) and enumerates specific return fields (tag, text, rect, attributes, visibility). However, it does not differentiate from siblings like 'safari_get_computed_style' or 'safari_query_all' which also retrieve element information.

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 no guidance on when to use this tool versus alternatives such as 'safari_get_computed_style' (for CSS-specific data) or 'safari_screenshot_element' (for visual capture). No prerequisites or conditions are mentioned.

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