glass_scroll

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

The annotation set is minimal (only three false flags: readOnlyHint, openWorldHint, destructiveHint), so the description bears full weight and exceeds expectations. It clarifies the click-to-event mapping ('clicks |dx| times'), explicitly contrasts wheel notches with pixels, and explains the app's autonomy over the final mapping ('is the app's choice'). This is outstanding disclosure of behavior beyond the structured data.

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?

The opening sentence is crisp, and the overall prose is well-proportioned. Some redundancy exists with the modifier description ('e.g.'-style language repeats in both the description and the `modifiers` field), but this is a minor fact, keeping it at a 4 rather than a 5.

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?

The description is complete for a majority of invocation scenarios, and the clause 'How an app maps a wheel notch to its view (lines, pixels, zoom) is the app's choice' is an honest, transparent disclosure of side effects. It misses the opportunity to point to `glass_scroll_to_element`, but is otherwise a thorough and complete description for a call to correctly filter this 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?

With schema description coverage at 100%, the baseline is 3. The description adds modest value by reinforcing key disambiguation like 'NOT pixels' and the clipping semantics, though these are largely mirrored in the schema documentation itself, keeping the description from a perfect score.

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 'Scroll at window-relative coordinates by (dx,dy) wheel steps' states a precise verb (Scroll) and a specific, well-defined resource (window-relative coordinates). The unit (wheel notches) is unambiguous, making it clear what the tool does and how it differs from a scroll-to-element or a pixel-based scroll. It leaves no ambiguity about its core purpose.

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 gives no guidance on when to choose this tool over an alternative, especially the sibling `glass_scroll_to_element`. There is no when/when-not stated, and no mention of alternatives, leaving the decision entirely to the caller. This is a clear gap in usage guidance.

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