Drag one element onto another. source_ref is the element to grab; target_ref is where to drop. Both are CSS selectors. Used for slider captchas, kanban, drag-and-drop uploads.
| Name | Required | Description | Default |
|---|---|---|---|
| page_id | Yes | ||
| source_ref | Yes | ||
| target_ref | Yes | ||
| in_workspace | No | Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected. |
Changes observed during successful MCP inspections.
Input schema / properties / in_workspaceAdded value: +{
+ "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+ "type": "integer"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds nothing behavioral beyond that - it does not say whether elements must be visible/scrolled into view, how the drag is stepped, or whether it can time out. Note the mild tension: a tool used for kanban is not obviously read-only/idempotent, but the description makes no explicit contradicting claim.
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?
Four short sentences, front-loaded with the action, then operand clarification, then use cases. Every sentence adds distinct information with no redundancy.
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?
No output schema exists and none is needed for a UI action; the description covers the action, both operands and typical scenarios. It leaves page_id context and any wait/visibility prerequisites unaddressed, so it is strong but not fully complete.
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 only 25%, so the description must carry the load, and it does for the two decisive params: source_ref is 'the element to grab', target_ref is 'where to drop', both CSS selectors. page_id is left unexplained, keeping it short of a 5 given the low schema support.
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 resource ('Drag one element onto another') and immediately identifies the two operands, so the action is unambiguous. It implicitly separates itself from browser_click/browser_hover by being a drag, but never names or distinguishes a sibling explicitly.
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 final clause gives concrete use cases ('slider captchas, kanban, drag-and-drop uploads') that tell the agent when this tool applies rather than a plain click. It offers no exclusions or named alternatives, so it stops short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.