Scroll the page

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

Beyond the annotations, it discloses two genuinely useful traits: mouse-wheel steps at a human pace (anti-bot pacing) and that a permission prompt is raised once per profile. The annotations already cover the safety profile (non-destructive, open-world), so this added behavioral context is the real value here. It still does not say what happens when scrolling past the end of the document.

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 compact sentences that front-load the core action and then add the pacing and prompt behavior. Nothing is wasted, though "Asks once per profile" is terse enough to be slightly cryptic on first read.

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 three-parameter interaction tool with no output schema, the definition covers the action and its pacing but leaves the identity parameter and the result of the call (scroll position, errors at boundaries) undocumented. Adequate to invoke, not complete enough to predict behavior.

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 description coverage is 0%, so the description must compensate. It does explain the amount parameter's accepted forms ("a page, half a page, or a number of pixels") and direction, but profileId — a required parameter — is never described, and the 50–5000 pixel bounds are left entirely to 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?

The description names a specific verb and resource ("Scrolls the main tab up or down") and specifies the granularity of movement (page, half page, or pixels). It is clearly distinguishable from siblings such as page_click or page_screenshot, though it never explicitly contrasts itself with 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 only implied: an agent can infer this is for moving the viewport, but there is no explicit statement of when to choose this over page_press_key or page_snapshot, and no note on when scrolling is unnecessary or harmful (e.g. at page boundaries).

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