Manage tabs within the same BrowserContext as page_id. action ∈ {list, switch, close, new}. For list, returns all open tab metadata; for new, returns the new tab's page_id.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| action | Yes | ||
| tab_id | No | ||
| page_id | 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?
The description advertises `close` (terminates a tab) and `new` (creates a tab), which are state-mutating operations, while the annotations declare readOnlyHint=true and destructiveHint=false. This directly contradicts the structured safety profile, which is the exact scenario the rubric treats as a contradiction.
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 dense sentences, front-loaded with scope, then the action set and return behavior. No wasted words, though the return-value sentence could be deferred and the action set could be formatted more scanably.
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 multi-action tab tool with no output schema, the description covers the key actions and even sketches return values for `list` and `new`, which is helpful. However, it omits the semantics of the optional `url`/`tab_id`/`in_workspace` parameters and never addresses the read-only framing that its own annotations assert.
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?
With only 20% schema description coverage, the description must carry the load. It valuably enumerates the `action` values (absent from the schema, which types `action` only as a bare string) and explains the role of `page_id`, but leaves `url`, `tab_id`, and `in_workspace` semantics unexplained, so it only partially compensates.
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 gives a specific verb+resource ('Manage tabs within the same BrowserContext as page_id') and enumerates the supported actions, so an agent knows exactly what the tool does. It does not explicitly differentiate itself from close siblings like browser_open or browser_close, keeping it just below a 5.
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?
Listing `action` ∈ {list, switch, close, new} implies the usage contexts, but there is no explicit guidance on when to choose this tool over browser_open, browser_close, or present_tab, nor on which action applies in which situation. Usage is inferable but not stated.
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.