Scroll

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

The annotation only says readOnlyHint=false, which is consistent with a page interaction. The description adds genuinely useful behavior beyond that: "Humanized wheel events by default" signals that real wheel events are dispatched, which can trigger lazy loading or sticky-header effects. It does not disclose whether the call waits for scroll completion, whether scrolling is smooth or instant, or that the "default" implies a non-default mode exists.

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?

Two short sentences, front-loaded with the verb and the modes, with no filler. The trailing "by default" clause is slightly ambiguous about what the alternative is, but the definition stays tight.

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 4-parameter interaction tool with no output schema and only a single non-read-only annotation, the description covers what the tool does but leaves gaps an agent would care about: whether it returns the resulting scroll position, whether it waits for the page to settle, and what "element into view" requires.

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 75%, with ref, selector, and amount already documented (including the 600px default). The description reinforces the direction/amount pairing and the top/bottom enum values and implies ref is needed for element-into-view, but adds no syntax or precedence detail beyond the schema's own "Preferred over selectors" note.

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") plus the three operating modes: direction/amount, top/bottom, and element-into-view. An agent can tell this apart from navigate, back, or press without opening the schema, though no sibling is named explicitly.

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?

There is no when-to-use or when-not-to-use guidance and no named alternative (e.g. evaluate for scripted scrolling, wait after scroll-triggered lazy loads). The only implicit cue is that "bring an element into view" pairs with a snapshot ref, which the agent must infer.

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