nexus-browser

Overview Schema Source Related Servers Discussions Admin

browser_new_tab

Opens a new Chrome tab at a given URL or about:blank and returns its tab_id for later commands, running in the background in an agent-named tab group without taking user focus.

Instructions

Opens a new Chrome tab at the given URL (or about:blank) and returns its id: the tab_id to pass to every following command. The tab belongs to THIS agent session (enforced by the extension).

By default in the background (background=True) without stealing the user's focus, in the tab group named after the agent (Antigravity, Claude or Codex); group="": no group. Only http, https, data: or about:blank URLs (never file://, chrome://).

Input Schema

Name	Required	Description	Default
`url`	No
`group`	No
`background`	No

Output Schema

Name	Required	Description
`data`	Yes
`status`	Yes
`warning`	No	Emergency stop hotkey not held, or similar notice
`untrusted_note`	No	Page text that looks like instructions aimed at an AI

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedv2.31.6Oct 29, 2026

addedOutput schema / $defs

Added value: +{
+  "NewTab": {
+    "additionalProperties": true,
+    "description": "Tab just opened: id is the tab_id for every following command.",
+    "properties": {
+      "groupId": {
+        "type": "integer"
+      },
+      "id": {
+        "type": "integer"
+      },
+      "index": {
+        "type": "integer"
+      },
+      "owner": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "pendingUrl": {
+        "type": "string"
+      },
+      "protected_page": {
+        "type": "boolean"
+      },
+      "status": {
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      },
+      "warning": {
+        "type": "string"
+      },
+      "windowCreated": {
+        "type": "boolean"
+      },
+      "windowId": {
+        "type": "integer"
+      }
+    },
+    "title": "NewTab",
+    "type": "object"
+  }
+}

addedOutput schema / additionalProperties
```
Added value: +true
```
addedOutput schema / description
```
Added value: +"The tab just opened."
```

addedOutput schema / properties / data

Added value: +{
+  "$ref": "#/$defs/NewTab"
+}

removedOutput schema / properties / result

Removed value: -{
-  "title": "Result",
-  "type": "string"
-}

addedOutput schema / properties / status

Added value: +{
+  "const": "success",
+  "type": "string"
+}

addedOutput schema / properties / untrusted_note

Added value: +{
+  "description": "Page text that looks like instructions aimed at an AI",
+  "type": "string"
+}

addedOutput schema / properties / warning

Added value: +{
+  "description": "Emergency stop hotkey not held, or similar notice",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "status",
+  "data"
+]

changedOutput schema / title

Previous value: -"browser_new_tabOutput"New value: +"NewTabAnswer"

First observedv0.1.0Oct 26, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare openWorldHint=true, destructiveHint=false, and readOnlyHint=false, and the description adds real value beyond them: the tab is scoped to THIS agent session (enforced by the extension), it is created without stealing user focus, it lands in the agent-named group, and only http/https/data/about:blank URLs are accepted. It does not discuss tab-count limits or what happens on failure, keeping it below the top score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the core action and return value, then defaults and URL restrictions. The nested parenthetical ("Antigravity, Claude or Codex") is slightly noisy but not wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values needn't be detailed, and the description still notes the tab_id contract. Combined with the URL-scheme restriction and session-ownership note, an agent has what it needs to call it correctly; only the sibling differentiation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden and does: url may be omitted to get about:blank, group="" means no group versus the default agent-named group, and background defaults to true with the meaning (no focus steal) spelled out. All three parameters gain semantics absent from the bare schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (opens a new Chrome tab), notes the optional URL default, and explains that it returns the tab_id used by every following command. It never explicitly distinguishes itself from the sibling browser_navigate, which also targets a URL, so an agent must infer the difference from the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The default behavior (background=True, no focus steal) and the group="" escape hatch imply the intended usage context, but the description never says when to call this versus browser_navigate (reuse the current tab) or browser_adopt_tab/browser_list_tabs. Usage is implied rather than stated.

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

Deploy Server