Touchpoint

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

Lacks annotations, so description carries full burden. Documents positional dependency (cursor must be positioned first) but omits safety profile, idempotency, side effects on UI state, or the fact that it operates on the element under cursor vs window-level scrolling.

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?

Well-structured with clear prerequisite statement followed by Args documentation. Slightly verbose formatting ('Args:') but every clause provides necessary information given lack of schema descriptions.

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?

Adequate for a 2-parameter automation tool. Prerequisites and parameter semantics are covered. Output schema exists (per context signals), so absence of return value documentation is acceptable.

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?

Effectively compensates for 0% schema description coverage by documenting both parameters: direction specifies valid enum values ('up', 'down', 'left', 'right') missing from schema, and amount clarifies units ('scroll ticks') and default value (3).

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 specific action (scroll) and location constraint ('at the current cursor position'), which distinguishes it from viewport-level scroll operations. Verb is clear but could specify 'scroll wheel' or 'scroll element' to eliminate ambiguity.

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 declares prerequisite workflow: 'Move the cursor to the target area first with mouse_move(), then call scroll().' Names specific sibling tool (mouse_move) and establishes temporal ordering, which is critical for correct invocation.

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