mac_scroll

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

With no annotations, the description carries the full behavioral burden and does add an important side effect: it moves the pointer over the target window first. It does not disclose permission requirements, behavior when no window is frontmost, whether scrolling is smooth or instant, or what the tool returns.

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 definition is a single front-loaded sentence with zero waste. It packs the action, target, parameters, default, and pointer side effect into one readable line.

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 simple two-parameter tool with no output schema and no annotations, the description covers the action, target, both parameters, the default, and a notable side effect. It is nearly complete, with only permission and failure-mode details missing.

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, and it does: it defines the direction domain as up/down/left/right and states the pages parameter defaults to 1. It does not clarify whether fractional or negative page values are valid, but both parameters receive meaningful semantic context.

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 uses a specific verb and resource ('Scroll the frontmost window') and scopes it to Mac frontmost-window scrolling. It implicitly distinguishes from browser_scroll and phone_scroll by naming the frontmost window, but does not name a sibling explicitly as the high-scoring example does.

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 implied by the context of scrolling the frontmost window, and the default page count is stated. However, there is no explicit guidance on when to use this versus mac_key, mac_drag, or other navigation tools, nor any prerequisites or exclusions.

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