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 of behavioral disclosure. It adds value by specifying the computed 'external/nofollow detection' capability beyond simple attribute extraction, but fails to disclose whether the operation is read-only, the output data structure, or any performance limitations (like the default limit of 100 implied by the schema but not mentioned).

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, efficient sentence with no wasted words. Each component (href, text, rel, target, external/nofollow) communicates specific functionality. It appropriately front-loads the action ('Extract') and resource ('links') before detailing attributes.

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 the absence of an output schema, the description partially compensates by enumerating the extracted fields, giving the agent a hint about the return structure. However, for a browser automation tool with many siblings, it should ideally clarify that it operates on the current active page and mention the default limit behavior described in the schema.

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?

The input schema has 100% description coverage for both parameters (limit and filter), establishing a baseline score of 3. The description does not add additional semantic context about these parameters (e.g., explaining that filter matches against URL or text substrings), but no additional compensation is needed given the complete schema 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?

The description clearly states the tool extracts links and specifies the exact attributes captured (href, text, rel, target) plus detection features (external/nofollow). It effectively distinguishes from sibling tools like safari_extract_images and safari_extract_tables by specifying the 'links' resource. However, it omits that it operates on the current page, which would provide complete clarity.

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?

The description provides no guidance on when to use this tool versus alternatives like safari_query_all or safari_get_element for link retrieval. There are no prerequisites mentioned (e.g., requiring navigation to a page first) and no exclusions or warnings about edge cases.

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