browser_scroll

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

With no annotations, the description carries the full burden and does deliver: it states the return value (updated page snapshot) and adds a prompt-injection safety warning about untrusted web content. It omits whether scrolling is viewport-only or persistent, and what happens with a stale ref, but the safety disclosure and return-value statement are meaningful context beyond the schema.

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 tight sentences, front-loaded with the core action and modes, then the return value and safety note. Zero filler and nothing 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?

For a 7-parameter, all-optional tool with no output schema, the description covers modes, return value, and the untrusted-data caveat, which is close to sufficient. Minor gaps remain (stale-ref behavior, interaction of snapshot=false with other steps), keeping it just under a 5.

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 100%, so every parameter (x, y, ref, deltaX, deltaY, snapshot, screenshot) is already documented in the schema. The description reinforces the ref/x/y mode relationship but adds no syntax or format detail beyond what the schema provides; baseline 3 applies.

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 (Scroll) and enumerates the distinct modes: at an element ref, at an x/y point, at the viewport middle, or ref-only to scroll into view. An agent can immediately distinguish this from sibling read tools like browser_snapshot or browser_screenshot without opening any 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?

The description explains which input combination triggers which behavior (ref vs x/y vs default viewport center, and ref-only for scroll-into-view), which is genuine when-to-use guidance for this tool. It does not, however, contrast against alternatives such as browser_navigate or when scrolling is unnecessary, so it stops short of explicit exclusions.

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