Skip to main content
Glama

browser_tabs

Manage browser tabs within isolated Playwright sessions to resolve session conflicts and enable concurrent browsing tasks.

Instructions

Manage tabs

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
indexNo

Implementation Reference

  • index.js:367-380 (registration)
    The 'browser_tabs' tool is registered using server.tool, and it uses proxyToolCall to delegate the execution.
    server.tool('browser_tabs', 'Manage tabs', {
      action: z.enum(['list', 'new', 'close', 'select']),
      index: z.number().optional()
    }, async (args) => {
      // 'new' action can work without active page, others require it
      if (args.action !== 'new') {
        const check = requireActivePage();
        if (check) return check;
      }
      const result = await proxyToolCall('browser_tabs', args);
      // 'new' action creates a page
      if (args.action === 'new' && !result.isError) {
        hasActivePage = true;
      }
Behavior1/5

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

No annotations are provided, placing full burden on the description. The description discloses no behavioral traits: it doesn't explain side effects of 'close' vs 'new', authentication requirements, rate limits, or what 'select' implies. With no readOnlyHint or destructiveHint, the agent cannot determine safety profile from either source.

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

Conciseness2/5

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

While brief (two words), this constitutes under-specification rather than efficient conciseness. The single 'sentence' adds no value beyond the tool name itself, failing the criterion that every sentence must earn its place.

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

Completeness1/5

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

For a tool with 2 parameters, 0% schema coverage, no annotations, no output schema, and 4 distinct enum-driven behaviors, the description is grossly incomplete. It omits critical operational semantics that would enable correct invocation.

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

Parameters1/5

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

Schema description coverage is 0%, requiring the description to compensate for undocumented parameters. The description fails to explain the 'action' enum values (list/new/close/select) or the purpose of 'index' (which actions require it, is it 0-indexed?).

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

Purpose2/5

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

The description 'Manage tabs' is essentially a tautology that restates the tool name 'browser_tabs'. It uses the generic verb 'manage' without specifying the supported operations (list, new, close, select) or distinguishing from siblings like 'browser_close' (which closes the browser, not tabs).

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

Usage Guidelines1/5

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

No guidance provided on when to use this versus siblings like browser_close, browser_navigate, or when specific actions are appropriate. No mention of prerequisites or workflow context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/OMGEverdo/browser-pool-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server