safari_run_script

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

With no annotations, the description carries the full behavioral burden and does substantial work: it explains receipt-based tab recovery across Safari windows, the exact constraints of clickAndOpenPopup (single target, background tab, CAPTCHA refusal, no query/hash return), and legacy mode differences. It stops short of describing failure handling, per-step return values, or whether steps abort on error, but the disclosed quirks are genuinely valuable.

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 dense but not padded; every clause earns its place, and the batching purpose is front-loaded. The long action list is necessary given the breadth of the tool, though formatting it as a structured list rather than a single run-on paragraph would improve scannability.

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 high-complexity batching tool with no output schema, the description covers the action set, key edge cases, profile-mode behavior, and receipt handling. It does not describe what the tool returns, how errors propagate across steps, or whether steps execute atomically, which an agent might need for robust invocation, but the provided context is unusually thorough.

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 schema already documents the steps array and its action/args shape, giving full coverage, so the baseline is 3. The description adds meaning by listing the valid action names and detailing the semantics of ambiguous ones like switchTab and clickAndOpenPopup, which is critical because the schema has no enums or per-action argument 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 first sentence states the tool's purpose precisely: batching Safari actions in one MCP session. The description then enumerates supported actions, making its scope explicit and distinguishing it from the many single-action sibling tools like safari_click or safari_navigate.

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 clearly frames when to use the tool — for batching multiple actions in one session rather than calling separate tools. It adds operational guidance such as using getReceipt after a cross-origin redirect and notes the legacy action set in non-profile mode, but it does not explicitly say 'do not use this for single actions when a dedicated sibling exists.'

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