gmail_scroll

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

It correctly states that the visible rows are returned along with absolute index values and an 'indexed' flag, and it specifies how an open conversation differs. These caveats are the main behavioral risk in this tool. It does not state whether the scroll changes app state or has side effects, so it does not reach a 5.

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 purpose and the 'top' behavior come first, and the indexing caveat follows in a tight second sentence. The nested parentheticals make it dense, but nearly every clause conveys a real constraint.

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?

With no annotations and no output schema, the description still explains the return shape (visible rows, absolute index, indexed flag) and conversation behavior. The main gap is how many rows one swipe returns and what happens at the end of the list.

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% and both parameters are documented, so the schema carries most of the weight. The description adds meaning beyond the schema by noting that direction=top always produces numbered rows, which clarifies the enum's semantics.

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?

It states a specific verb (scroll), the resource (the current Gmail list or open conversation), and the special 'top' behavior. The reference to the list last returned by gmail.list / gmail.search / gmail.scroll distinguishes it from those siblings and from the generic ui_scroll.

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 gives a clear usage context (paging through a Gmail list or conversation) and a precondition for index usability (the list must be the one last returned by gmail.list / gmail.search / gmail.scroll). It does not explicitly say when to prefer it over the sibling ui_scroll/ui_swipe, which keeps it from a 5.

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