Scroll

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose one genuinely useful trait — that the tool reports the actual resulting position (not just the requested delta) — but says nothing about permissions, whether the scroll animates/blocks, or failure behavior when a ref is stale.

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?

One sentence, front-loaded with the action and the two modes, then the modifiers. No wasted words and nothing important buried.

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 output schema, the note that it reports the resulting position is important and present. The description adequately covers the tool-specific parameters; it could say a bit more about return shape or ref failure, but for a simple scroll action it is close to 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?

The schema leaves dy and ref entirely undocumented while covering the shared params (slot, tab, agent, summary, read) at ~75%. The description fills exactly that gap by defining dy's sign convention and default and explaining what ref does, which is real value beyond 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?

States a specific verb ('Scrolls') plus the two resources/modes it operates on: a ref element into view, or by dy pixels. No sibling tool in the list does scrolling, so differentiation is implicit and unambiguous.

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?

Gives the mechanics of dy (positive = down, negative = up, default 600) but never says when to prefer ref-scrolling over dy-scrolling, or when scroll is needed versus browser_wait/snapshot. Usage is implied rather than guided.

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