Scroll

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

With no annotations at all, the description carries the full burden and does a reasonable job: it explains what untilStable actually does (keeps scrolling while an infinite feed loads), that it reports growth, and that it locates the real scroll container. That is genuine behavioral context beyond the schema, though it omits return format for the normal scroll case.

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?

Three sentences, front-loaded with the core action and then the two special behaviors. Tight and free of filler, though the second sentence is somewhat dense.

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, zero-annotation, no-output-schema tool, the description covers the interesting semantics well but leaves several parameters and the general return value unexplained. Adequate but with clear gaps.

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 50%. The description adds meaning for a few parameters by explaining 'by' pixels, 'to' top/bottom, and the untilStable behavior, but ref, selector, tabId, direction, and maxRounds get no prose explanation. It partially compensates but leaves half the parameters undocumented.

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 resource (page or element) with its modes: by pixels or to top/bottom. It is clear what the tool does, though it does not need to distinguish itself from siblings since no other tool in the list scrolls.

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?

It implies when to use it (untilStable for infinite feeds, real scroll container in app layouts), which gives implicit usage context. However there are no explicit when-not conditions or alternatives named, and nothing tells the agent when scrolling is the wrong move versus using browser_look or browser_extract.

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