Safari MCP Server

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

With no annotations provided, the description carries full behavioral disclosure burden. It explains the character-by-character execution model, realistic key event simulation, and critical state constraint that 'refs expire after each new snapshot.' Does not explicitly address error handling or event trigger specifics (blur/focus), but covers primary behavioral traits well.

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?

Four sentences with zero waste. Front-loaded with mechanism, followed by two specific alternative recommendations, and ending with a critical operational warning about ref freshness. Every sentence earns its place with high information density.

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 moderate complexity (3 params, no output schema, no annotations), the description is comprehensive. It covers selection criteria, sibling differentiation, and parameter prerequisites. Could marginally improve by indicating success/failure indicators or timeout behavior, but otherwise 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?

Schema coverage is 100%, establishing baseline documentation for all three parameters. The description adds crucial semantic context not in the schema: the requirement to use a 'FRESH safari_snapshot' when using the 'ref' parameter due to expiration behavior. This operational constraint is essential for correct invocation.

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?

Explicitly states the mechanism ('character-by-character with realistic key events') and target resource (text input fields). Clearly distinguishes from siblings by contrasting with safari_fill (framework-native APIs) and safari_replace_editor (code editors).

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 'Best for' guidance (search boxes, chat inputs, autocomplete fields) and named alternatives for incompatible scenarios ('use safari_fill instead' for rich text, 'use safari_replace_editor' for code editors). Includes prerequisite instruction about taking a fresh snapshot when using refs.

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