browser_open

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

No annotations provided, so description carries full burden. It discloses idempotent launch behavior, preference for existing endpoints, destructive warning for killExisting (loss of unsaved input), and per-process CDP limitation. Thoroughly covers behavioral traits.

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?

Single paragraph (~100 words) that efficiently covers purpose, usage, return format, and caveats. Every sentence contributes essential information without redundancy.

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?

Covers connection, launch, return structure, and prerequisites. Lacks error behavior details but given no output schema and simple return array, the description is nearly complete. Minor gap: no mention of what happens on timeout or port conflict.

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 already provides 100% description coverage for all parameters. Description adds value by elaborating on launch parameter's idempotency (prefers existing endpoint, skips spawn) and explains how returned tabId is used with sibling tools, but extra context is modest.

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?

Description clearly states verb+resource: 'Connect to Chrome/Edge... and return open tab IDs'. It distinguishes from siblings by explicitly stating it's 'required before all other browser_* tools', setting it apart as the prerequisite connection tool.

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?

Provides explicit when-to-use: 'required before all other browser_* tools'. Details when to use launch parameter vs pure connect, and includes caveats about Chrome restarts and inability to take over non-debug sessions, effectively guiding agent's decision.

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