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 well: it discloses auto-detection of scroll containers, self-terminating behavior when height stops growing, and a subtle environmental failure mode (background tabs render no frames, IntersectionObserver lists may refuse to grow, and the tool reports this). It does not mention auth/permission needs or the return/diagnostic shape beyond implying it signals the stale-tab 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?

Four compact sentences, front-loaded with the core action, then behavior, then alternative, then the caveat. Nothing is redundant and every sentence adds decision-relevant information.

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?

No annotations and no output schema, so the description must supply behavioral context; it covers behavior, limits, and a known failure mode well. It does not describe what the tool returns on success (e.g., how much was loaded, whether a diagnostic is returned), which is the main remaining gap for a 7-parameter tool.

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 86%, so the schema already documents nearly all 7 parameters (ref, wait, times, tabId, etc.). The description adds no parameter-level detail such as units, interactions between 'times' and 'wait', or how 'to' behaves with a specific 'ref', so it stays at the baseline for high-coverage schemas.

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 target ('Scroll to load more of a lazy list') and immediately scopes the behavior ('Auto-detects inner scroll containers, stops early once height stops growing'). An agent can distinguish this from sibling tools like fetch/network purely from the text.

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?

Explicitly routes the agent to an alternative ('Prefer network/fetch for bulk data') with the condition that selects it. It also names the scenario where the tool should be used (lazy lists) and a known failure context (background tabs with IntersectionObserver). No explicit 'when-not' for other interaction siblings, but the routing guidance is strong.

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