Drag

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

With no annotations, the description carries the burden and delivers real behavioral value: it discloses the execution mechanism ("real mouse: press → move in steps → release") and a non-obvious implementation detail ("HTML drag is handled without starting an OS drag"). It omits failure semantics, auto-scroll behavior, and any permission/side-effect context, keeping it below a 5.

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, front-loaded with the action and mechanism before the target options, with zero filler. The use-case enumeration doubles as routing signal rather than padding.

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 an 11-parameter mutation-style browser action with no annotations and no output schema, the description covers the essentials: what it does, how it does it, target specification, and the HTML-drag special case. Slots, tabs, and the read/summary params are fully documented in the schema, so nothing critical is missing, though side-effect and error behavior are unaddressed.

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 selection-level meaning the schema does not: it groups to / to_text / dx+dy as the three alternative ways to specify the drop location (element ref, visible text, or pixel offset). That framing helps an agent choose among 11 params rather than blindly reading them.

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?

Names a specific verb+resource ("Drags with the real mouse") and immediately enumerates the distinguishing scenarios: drag and drop, sliders, reordering, drag CAPTCHAs. The contrast with browser_click (drag-and-drop vs. discrete click) is inferable from the use-case list without opening either schema.

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?

Gives clear context for when to reach for this tool via the enumerated drag scenarios, which implicitly distinguishes it from sibling action tools like browser_click or browser_press_key. It does not name an explicit alternative or state when-not to use it (e.g. single-click targets), so it stops short of full routing guidance.

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