Safari MCP Server

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

Without annotations, the description carries full burden. It successfully discloses output content types (roles, labels, states) but fails to mention safety characteristics (read-only vs destructive), side effects, or performance implications that annotations would typically cover.

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 efficiently structured sentences: the first defines the operation and parenthetically lists return data types; the second establishes the use case. Zero redundancy, every word earns its place.

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 no output schema exists, the description compensates well by enumerating the specific data categories returned (roles, ARIA labels, etc.). Missing only minor details like return format structure or pagination behavior for deep trees.

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?

Schema coverage is 100% (selector and maxDepth fully documented), establishing baseline 3. The description adds no parameter-specific semantics, but the schema handles this adequately without needing elaboration in the prose.

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?

Clear specific verb ('Get') + resource ('accessibility tree') and distinguishes from sibling 'safari_snapshot' by explicitly listing a11y-specific data types returned (roles, ARIA labels, focusable elements, form states).

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 clear usage context via 'Essential for a11y auditing,' indicating when to use this tool over generic page analysis tools. Lacks explicit 'when not to use' guidance or named alternatives, though the specialized scope implies differentiation.

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