Safari MCP Server

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

No annotations provided, so description carries full burden. It discloses the scrolling mechanism for text mode ('scrolls down until text appears in DOM'), which is crucial for virtual DOM handling. However, it omits error behavior (what happens if timeout exceeded?), directionality constraints, and whether the operation is idempotent or state-changing.

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?

Two sentences, zero waste. First sentence establishes the dual input methods. Second sentence provides the specific virtual DOM use case. Information is front-loaded and dense. Every clause earns its place by conveying distinct operational modes or constraints.

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 this is a focused 4-parameter tool with complete schema coverage and no output schema, the description adequately covers the primary use case and the important edge case (virtual DOM/lazy loading). It could improve by mentioning error conditions or behavior when neither parameter is provided, but it is sufficiently complete for an agent to invoke correctly.

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 coverage, baseline is 3. The description adds valuable context about the relationship between parameters (OR logic) and specifically when to use 'text' over 'selector' (virtual DOM cases). It does not add syntax details or format constraints beyond the schema, but the virtual DOM guidance is meaningful added value.

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 tool scrolls to elements using CSS selectors OR text content. The dual-mode approach is explicit. However, it doesn't explicitly differentiate from siblings like 'safari_scroll' (likely directional) or 'safari_scroll_to' (likely coordinate-based), though the element-targeting focus is implied.

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 specific guidance for virtual DOM scenarios (Airtable): 'use text — scrolls down until text appears'. This is valuable context for lazy-loading interfaces. However, it lacks explicit when-to-use/when-not-to-use guidance comparing it to the 60+ sibling tools, particularly the other scroll variants.

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