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 usefully discloses direction semantics and that the resulting position is reported, but says nothing about permissions, multi-slot/tab interaction, or side effects on page state.

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?

A single dense sentence that front-loads the verb and the two modes, with no wasted words. Direction and default are packed in parenthetically without distraction.

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 an 8-parameter action tool with no output schema, the description covers the core scroll mechanics; remaining parameters (read, slot, agent, summary, multiSlot) are documented in the schema. Reporting the resulting position compensates for the missing output schema, leaving only minor gaps around tab/multi-slot context.

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?

With 75% schema coverage, the baseline is 3, but the description adds real meaning beyond the schema: the dy parameter has no schema description, and the description supplies sign convention (positive=down, negative=up) and the default of 600, plus clarifies that ref targets a ref element.

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) with two distinct modes: a ref element into view, or by dy pixels. It's clearly distinguishable from siblings like browser_click or browser_wait, though it doesn't explicitly name them.

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?

Usage is implied by the ref-vs-dy alternative, but the description never states when to prefer scrolling a ref into view versus offset scrolling, nor when scroll is preferable to browser_wait or a snapshot. No explicit exclusions or prerequisites are given.

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