Safari MCP Server

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

With no annotations provided, the description carries the full burden. It mentions 'viewport visibility' which hints at behavioral logic, but fails to disclose whether this is read-only, how it handles lazy-loaded images, or what happens when no images are 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?

The description is a single, information-dense sentence with zero waste. Every word (src, alt, dimensions, loading strategy, viewport visibility) earns its place by specifying exactly what data is returned.

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 simple extraction tool with one parameter and no output schema, the description is nearly complete. It effectively documents the return value structure by listing extracted fields, though it could clarify that this is a read-only operation.

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 description coverage is 100% for the single 'limit' parameter, so the baseline score applies. The description does not mention the parameter, but the schema fully documents it, making additional description unnecessary.

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 uses a specific verb ('Extract') and resource ('images'), and clearly distinguishes from sibling tools like safari_extract_links or safari_extract_tables by listing image-specific attributes: src, alt, dimensions, loading strategy, and viewport visibility.

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?

While the specific attributes imply this is for image analysis tasks, there is no explicit guidance on when to use this versus other extraction tools, prerequisites (e.g., requiring a loaded page), or when to prefer safari_screenshot instead.

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