List, create, switch between, or close browser tabs to control multiple pages during AI-driven automation.
List, create, switch between, or close tabs.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Tab id (e.g., t2) for switch/close. Takes precedence over index. | |
| url | No | Initial URL when action=new. | |
| index | No | Tab index (0-based) for switch/close. Defaults to active when omitted. | |
| action | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden and it does not deliver: it never says that 'close' destroys a tab and its state, whether switching changes the active context for subsequent calls, or what 'list' returns. For a tool containing both read and destructive operations with zero annotation coverage, this is a substantial gap.
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?
A single front-loaded sentence with no filler, and the operation list is easy to scan. It is arguably too terse, but that shortfall is captured in the other dimensions rather than being a structural flaw.
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?
With four parameters, no output schema, no annotations, and both mutating and destructive actions, the description should explain the close/switch semantics and what listing returns. It covers only the bare enumeration, leaving the agent without enough context to use the tool confidently.
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 75% and the schema already documents id, url, and index thoroughly, including the id-takes-precedence rule. The description's enumeration of the four actions merely restates the action enum and adds no parameter meaning beyond it, so it does not compensate for the uncovered fourth parameter.
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 names a specific resource (tabs) and enumerates the four operations (list, create, switch, close), so the agent knows exactly what domain this covers. It does not reference any sibling, but no sibling tool handles tab lifecycle, so differentiation is implicit rather than stated.
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?
There is no guidance on when to use this versus the many browser_* siblings (e.g., browser_navigate vs action=new), nor any prerequisites such as needing an open browser session. The agent must infer that tab management is a separate concern from navigation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.