Safari MCP Server

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

With no annotations provided, the description carries full disclosure burden. It effectively explains the interception mechanism (fetch/XHR), temporal limitations (non-retroactive), and operational constraints (once per page). Minor gap: doesn't mention how to stop/clear capture or data persistence, though siblings suggest clear functionality exists.

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?

Three tightly constructed sentences with zero redundancy. Front-loaded with the core action, followed by operational constraints, and closed with sibling differentiation. Every clause provides actionable guidance.

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 lack of output schema, the description adequately covers invocation requirements (frequency, timing constraints) and alternative selection. It provides sufficient context for an agent to correctly invoke the tool without needing to describe return values or retrieval mechanisms likely handled by sibling tools (safari_network, safari_network_details).

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?

Input schema contains zero parameters, establishing a baseline of 4 per scoring rules. The description correctly implies no configuration is needed for the basic capture operation, though it doesn't explicitly state 'no parameters required'.

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 specific verbs ('Start capturing') and identifies the exact resource ('network requests', specifically 'fetch + XHR') with detailed attributes ('headers, status, timing'). It clearly distinguishes from sibling tool 'safari_network' by contrasting detailed capture vs. quick overview.

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 explicit constraints ('Call once per page'), temporal scoping ('captures requests AFTER this call only'), and directly names the alternative tool ('use safari_network instead') for a different use case (already-loaded resources). This covers when-to-use and when-not-to-use comprehensively.

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