page_drag

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

The description adds meaningful behavioral detail beyond the annotations: it uses one CDP input sequence, runs in the background, never activates the tab, never moves the desktop cursor, and performs no hit-testing on either endpoint. These are exactly the side-effect traits an agent needs to know. The description is consistent with the annotations, including the destructiveHint and readOnlyHint flags.

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 two concise sentences with no filler. The primary action and tab context are front-loaded, and the coordinate semantics and behavioral caveats come immediately after. Every clause adds information an agent can act on.

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 drag tool with a relatively small parameter set, the description covers the core behavior, coordinate semantics, background execution, and hit-testing behavior. An output schema exists, so a return-value explanation is unnecessary. The main gap is that optional parameters like duration and button receive no context, though their defaults and intuitive names reduce the risk.

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 schema itself has 0% parameter description coverage, so the description must compensate. It does clarify the four required coordinate parameters by stating that both endpoints are viewport-relative CSS pixels and are not hit-tested. However, it says nothing about the optional button, duration, timeout, or session_id parameters, leaving those to be inferred from defaults or names.

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 states a specific action: drag between viewport coordinates in a specific tab. It also distinguishes itself from related tools by noting it runs as a background CDP input sequence, does not activate the tab, and does not move the desktop cursor. This gives an agent enough to separate page_drag from page_click, page_type, and similar input 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 gives clear behavioral context that implies when to use this tool: use it for viewport-relative drags that should happen in the background without tab activation or desktop-cursor movement. It even references page_click's coordinate mode as a point of comparison. It does not explicitly state when not to use it or name an alternative beyond the implicit page_click analogy, so it stops just short of full guidance.

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