Manage browser tabs: list, open, switch to, or close them, and automatically adopt and activate new tabs opened by a page.
List, open, switch to or close tabs. Tabs a page opens (target=_blank, window.open) are adopted and made active automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | For new | |
| index | No | For select and close: the tab's number in list, from 0 | |
| action | Yes | What to do |
Changes observed during successful MCP inspections.
v0.7.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The second sentence adds genuine behavioral value beyond the annotations: tabs spawned via target=_blank or window.open are adopted and made active automatically, which is non-obvious and affects the agent's mental model. However, with openWorldHint=true and readOnlyHint=false covering a mixed read/write tool, the description never warns that 'close' discards tab state or that list is a pure read — a relevant gap for a destructive action.
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 tightly written sentences, the action list front-loaded and the behavioral caveat second. No filler or repetition of schema content.
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 no output schema, the description could say what 'list' returns (tabs numbered from 0, per the index parameter hint), but the index description bridges enough of that gap. For a 3-parameter tab management tool, what remains missing is minor.
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 100%, so all three parameters are documented in the schema and the baseline is 3. The description adds nothing about url/index semantics, though the auto-adopt note indirectly informs how 'new' behaves.
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 concrete resource (tabs) and four specific verbs matching the action enum (list/open/switch/close), so an agent understands exactly what the tool manages. It separates itself from browser_navigate by being about tab lifecycle rather than page navigation, though it doesn't explicitly name that sibling.
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?
Usage is implied only through the enumerated actions; there is no statement of when to use this versus browser_navigate (navigate current tab) or browser_close (close the whole browser). The agent must infer the boundary from sibling names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.