Skip to main content
Glama
Brave Session MCP

Brave Session MCP

by MacStenk

brave_open

Destructive

Open an explicitly specified HTTP(S) URL in a new tab, with an optional wait for page load and settling before returning.

Instructions

Öffnet eine ausdrücklich angegebene HTTP(S)-Adresse in einem neuen Tab. wait wartet danach zusätzlich ab.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "brave_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
waitNoMillisekunden, die nach der Aktion auf das Laden der Seite und eine Beruhigungsphase gewartet wird. Weglassen oder 0: sofort zurückkehren.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.1/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=true, so the description should add why this is treated as destructive and what side effects a load can cause. It only adds that the page opens in a new tab and that 'wait' adds a subsequent wait — useful, but it never mentions permissions, failure behavior, or that the call has real-world side effects.

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?

Two short sentences, front-loaded with the action and with zero filler. It is arguably too terse rather than padded, so terseness is penalized under completeness, not here.

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

Completeness2/5

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

This is a destructive/open-world action with no output schema, yet the description says nothing about what the return looks like, whether the new tab affects subsequent brave_tabs/brave_tabs state, or how failures are signalled. Given the annotations flag destructive behavior, an agent needs more context than is provided.

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

Parameters3/5

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

The description constrains 'url' to HTTP(S) addresses, which adds meaning beyond the schema's generic 'format: uri'. The 'wait' parameter is already fully documented in the schema ('Millisekunden ... Beruhigungsphase'), so the description's mention of it adds little, and with only 50% schema description coverage the remaining gap (url semantics) is only partly compensated.

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 concrete verb and object ('Öffnet eine ... HTTP(S)-Adresse in einem neuen Tab'), so an agent knows it launches a URL in a fresh tab rather than reusing the current one. It does not differentiate itself from the sibling brave_navigate, which is the obvious point of confusion for a URL-opening tool.

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 phrase 'ausdrücklich angegebene' implies use when a concrete URL is already in hand, and 'in einem neuen Tab' hints at the new-tab scenario, so usage is inferable. There is no explicit when-to-use/when-not guidance and no routing to brave_navigate for same-tab navigation.

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