scroll

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

With no annotations, the description carries the full burden, and it discloses an important behavioral trait: the frontmost application must be in the session allowlist or the call returns an error and does nothing. That failure mode is exactly the kind of context an agent needs. It still omits rate limits, return format, and whether a prior screenshot is required to obtain coordinates.

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 sentences, zero filler, with the action front-loaded and the precondition immediately following. Every sentence earns its place.

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?

Given a 3-parameter tool with 100% schema coverage and no output schema, the description only needs to add the invocation precondition, which it does. It is close to complete, though a hint about deriving coordinates from the latest screenshot would make the workflow self-contained.

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 coordinate, direction, and amount are already fully documented by the schema, including the enum and tick semantics. The description's 'at the given coordinates' adds no meaning beyond what the schema provides, so the baseline of 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 target (the given coordinates), which is enough for an agent to distinguish it from click/key/drag siblings. However, it does not name a sibling or scope the tool relative to alternatives like screenshot or mouse_move.

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?

There is no explicit when-to-use or when-not-to-use guidance, nor any named alternative. The allowlist sentence implies a precondition for successful invocation, which is real context, but it is a call-time constraint rather than usage routing.

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