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. While the verb 'Read' implies a non-destructive operation and it specifies returned content components (title, URL, body), it lacks details on error handling for invalid selectors, page load state prerequisites, or rate limiting behavior.

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 consists of four efficient sentences that progress logically from purpose to use cases to alternatives to parameter guidance. Every sentence provides distinct value without redundancy or filler content, making it appropriately front-loaded.

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 tool's straightforward purpose and comprehensive schema coverage, the description adequately covers essential context including return content structure and sibling differentiation. However, without an output schema, it could further clarify the exact format of the returned text (e.g., structured object vs. concatenated string).

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, establishing a baseline score of 3. The description adds imperative usage guidance ('Use selector to read specific element') that complements the schema's declarative definitions, but does not significantly expand semantic understanding of parameter validation rules or format constraints beyond the schema.

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 'Read[s] page text content (title, URL, body text)' providing specific verb, resource, and returned scope. It effectively distinguishes this from sibling tools by explicitly mentioning that for interacting with elements, one should prefer safari_snapshot instead.

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?

It provides explicit usage guidance stating 'Use for reading article text or page content' and contrasts this with safari_snapshot for element interaction scenarios. The description also includes imperative guidance on when to use specific parameters ('Use selector to...', 'Use maxLength to...').

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