page_drag

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

With no annotations provided, the description carries the full behavioral disclosure burden. It reveals that the drag uses one background CDP input sequence, does not activate the tab, does not move the desktop cursor, uses viewport-relative CSS pixels, and is not hit-tested. This is unusually rich behavioral detail beyond what the name or schema could convey.

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 focused sentences with no filler. The main action is front-loaded, and every additional clause adds useful clarification about coordinate space, background execution, tab activation, cursor movement, and hit-testing.

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?

The core behavior and coordinate semantics are well covered, and the output schema reduces the need to explain return values. However, the description says 'in a specific tab' but never connects that tab selection to the session_id parameter, and optional parameters like button, timeout, and duration lack the detail needed to invoke non-default behavior correctly.

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 description coverage is 0%, so the description must compensate. It clarifies x1, y1, x2, and y2 as viewport-relative CSS pixels, but it leaves button, timeout, duration, and session_id semantically unexplained. The description does not define units for timeout/duration, allowed values for button, or how session_id selects the 'specific tab' mentioned in the description.

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 uses a specific verb and resource: 'Drag between viewport coordinates in a specific tab.' It actively distinguishes itself from mouse_drag by coordinate system and from page_click's coordinate mode, so an agent can tell exactly what this tool does 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 description provides clear context: this tool works in a background tab, does not activate the tab, and does not move the desktop cursor. It also contrasts with mouse_drag's physical screen pixels, giving an explicit alternative for choosing the right tool. It does not list formal when-to-use/when-not-to-use conditions beyond that, but the guidance is strong.

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