scroll

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the multi-agent scoping model, the cross-agent rejection error (TAB_NOT_OWNED), a configurable cap with default and range, and the is_final session-clearing side effect. Gaps remain on edge behavior (e.g. scrolling past the end of a page, whether the operation is purely read-only) and the 'cap' is named without saying exactly what is capped.

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?

Front-loaded with purpose and return value, then organized under 'When to use', 'Related', and 'Multi-agent' labels, so the dense information is scannable. It is on the long side and the multi-agent sentence crams four separate facts together, but no sentence is filler.

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 6-parameter tool with no output schema, the description covers purpose, return value, usage, alternatives, error behavior, and session lifecycle. The only shortfall is that 'cap configurable (default 8, 1-64)' is unexplained, leaving the agent unsure what resource is being capped.

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%, so the baseline is 3. The description's only parameter-adjacent content — tab_id usage and the default one-viewport amount — largely restates what the schema already documents, so it adds little semantic value beyond the structured fields.

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 and resource ('Scroll the page up or down by a specified amount') plus the return value ('Returns new scroll position'). It also names the sibling tools it is NOT (scroll_to_top, scroll_to_bottom as 'quick jumps'), so an agent can distinguish it from the jump-style scrollers without opening a schema.

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?

Explicit 'When to use' clause gives three concrete triggers (bring off-screen content into view, load lazy-loaded content, navigate long pages), and the 'Related' clause routes to alternatives with their distinguishing trait. Nothing about tool selection is left to inference.

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