browser_click_xy

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

With no annotations provided, the description carries the full disclosure burden. It reveals two important behavioral traits: 'raw viewport coordinates' (meaning no scrolling or element lookup) and 'fully trusted mouse events' (which bypass some event trust restrictions). It also warns about unusual cases like Azure portal dialogs, Knockout-bound divs, and canvas UIs. However, it does not mention edge cases such as coordinates outside the viewport or page movement after a screenshot.

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 description is three sentences with zero filler. It front-loads the 'ESCAPE HATCH' label, then gives a crisp when-to-use and how-to workflow. Every sentence contributes purpose, usage context, or procedural guidance.

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 two-parameter tool with no output schema, this description is complete. It covers what the tool does, when to use it, how to get coordinates, and how to combine it with browser_screenshot. The omission of rare edge cases is acceptable because the tool is intentionally simple and the use case is clearly scoped.

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?

The input schema already has 100% coverage for both x and y, so the baseline is 3. The description adds value beyond the schema by explaining how to derive coordinates—'take a screenshot, read the button's position, click its center'—and explicitly emphasizing CSS pixel units and the viewport origin. This practical guidance helps the agent invoke the tool with meaningful inputs.

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 clearly identifies the tool as an escape hatch that clicks at raw viewport coordinates in CSS pixels with fully trusted mouse events. It explicitly contrasts this with selector-based strategies, naming the exact resource and action, so an agent can distinguish it from browser_click and other sibling click tools.

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 explicitly states when to use it: 'when a visible button resists every selector strategy' and provides a concrete workflow with browser_screenshot. It doesn't name the preferred alternative (browser_click) explicitly, but the 'escape hatch' framing and 'resists every selector strategy' strongly imply the fallback nature, which is enough guidance without being fully explicit.

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