safari_snapshot

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

With no annotations, the description carries the disclosure burden. It reveals that the tool returns a structured accessibility tree with ref IDs, is cheaper than a screenshot, and that refs are for use with click/fill/type actions. This covers the key behavioral trait beyond a simple 'return snapshot' statement, though it leaves out any error or edge-case 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 is front-loaded with the core purpose, and every sentence contributes either a capability, a workflow, or a comparative preference. No filler or repetition.

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?

The description provides a complete picture of the tool's output and usage for an agent to start with refs, and the schema covers the parameters. However, given the absence of an output schema and the presence of a similarly named sibling, the description would benefit from explicitly noting the relationship or difference to safari_accessibility_snapshot.

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 description coverage is 100%, so the baseline is 3 regardless of description content. The description adds no parameter-specific nuance beyond the workflow example; receipt and selector are already fully documented in 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 identifies safari_snapshot as a tool for capturing page state as an accessibility tree with interactive ref IDs, and contrasts it with safari_screenshot and safari_read_page. However, it fails to distinguish it from the closely named sibling safari_accessibility_snapshot, leaving ambiguity about which snapshot-style tool to choose.

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 gives explicit guidance on when to prefer this tool over safari_screenshot and safari_read_page, including a cost rationale and a workflow example. But it does not mention safari_accessibility_snapshot, which, given the name overlap, is a critical alternative that should be addressed to avoid mis-selection.

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