Drag

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

No annotations are provided, so the description must carry the behavioral burden, and it does disclose the underlying mechanism (real mouse press/move/release) plus the important distinction that HTML drag is handled without starting an OS drag. It omits failure modes (e.g. what happens if the drop target isn't reachable) and does not describe the response, though the schema's 'read' parameter covers post-action reading.

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?

Three tight sentences, front-loaded with the verb and mechanism, then targeting options, then the HTML-drag caveat. No filler and each clause carries distinct information.

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 action tool with no annotations and no output schema, the description covers the core behavior, drop-target alternatives, and the HTML-vs-OS drag distinction, while the schema fully documents slot/tab/agent/read/summary. It stops short of stating prerequisites (active tab, element visibility) or what a failed drag looks like.

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 already 100%, so 3 is the baseline, but the description adds real meaning by presenting 'to', 'to_text', and 'dx/dy' as the three alternative ways to specify the drop target and clarifying that dx/dy are relative to 'from' — a choice the schema lists but never frames as mutually exclusive options.

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 and mechanism ('Drags with the real mouse (press → move in steps → release)') and enumerates concrete use cases (drag and drop, sliders, reordering, drag CAPTCHAs). This clearly separates it from siblings like browser_click and browser_hover without needing to name them.

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 enumerated scenarios (drag and drop, sliders, reordering, CAPTCHAs) give clear context for when this tool applies, and the target-selection sentence tells the agent how to aim the drag. There is no explicit 'when not to use this / use X instead' guidance versus browser_click, which keeps it out of 5 territory.

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