browser_mouse

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds real operational context beyond them — coordinates are viewport CSS pixels (screenshot frame) or target-relative, and pointer/button state persists between calls, which is what makes drags possible. It omits failure modes (what happens if a coordinate is off-page) but covers the stateful behavior an agent most needs.

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?

Front-loaded with the core distinction before the mechanics, and packed into three dense sentences with no filler. Slightly telegraphic phrasing ('Raw mouse at a point') costs a fraction of clarity but the structure holds up.

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 10-parameter, stateful, open-world input tool with no output schema, the description covers action coverage, coordinate semantics, and state persistence — the three things needed to invoke it correctly. Return behavior is only hinted at via the snapshot parameter in the schema, and error conditions are unaddressed, but nothing essential is 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: the coordinate frame for x/y (viewport CSS pixels, or target top-left when one is given) and the fact that x/y become scroll deltas for wheel. That resolves the main ambiguity an agent would face when choosing between absolute and element-relative coordinates.

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+resource ('raw mouse at a point') and enumerates the exact actions (move, down, up, click, wheel). It also contrasts itself with element-based siblings by scoping to 'what has no element to aim at (a canvas, a map, a game)', so an agent can tell it apart from browser_click/browser_hover without opening schemas.

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 phrase 'for what has no element to aim at' gives a clear selection rule versus browser_click and browser_hover, and the drag/draw recipe ('down, moves, up') tells the agent how to compose calls. It stops short of explicitly naming browser_click as the alternative when an element does exist, so exclusion is implied rather than stated.

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