Safari MCP Server

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

Without annotations, the description carries the full burden. It valuably discloses the return format ('base64 PNG image') since no output schema exists, but omits other critical behaviors: whether it scrolls to the element, handles off-screen elements, or error behavior if the selector is not found.

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 with zero waste: first establishes the action and mechanism, second specifies return format. Information is front-loaded and appropriately sized for the tool's simplicity.

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?

Adequate for a single-parameter tool with complete schema coverage. The description compensates for the missing output schema by specifying the return format. However, given the visual nature of the tool, it should mention viewport/visibility considerations to be fully complete.

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, the baseline is 3. The description mentions '(by CSS selector)' which aligns with the schema but adds no additional semantic context (e.g., examples of valid selectors, syntax constraints) beyond what the schema already provides.

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 the action ('Take a screenshot'), target ('specific element'), and mechanism ('by CSS selector'). However, it does not explicitly differentiate from the sibling tool 'safari_screenshot' (likely full-page), leaving the agent to infer the distinction from the name alone.

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?

No guidance provided on when to use this element-specific screenshot versus the full-page 'safari_screenshot' or other visual capture tools. No prerequisites mentioned (e.g., element visibility requirements).

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