start_browser

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

No annotations are provided, so the description carries the full responsibility for behavioral disclosure. It clearly reveals that the session is persistent across tool calls, maintains browser state (cookies, tabs, history, storage), and runs until close_browser is called or the server exits. It explains the CDP-based communication versus WebDriver, the OS-dependent headless default, and the availability of fallbacks like use_chromium and browser_executable_path when the browser cannot be found.

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?

The description is longer than the average MCP description, but the added length is purposeful: each block (Args, Returns, Lifecycle, Environment requirements) adds non-redundant integration-level detail. It could be slightly tightened by folding the OS-specific headless rules into one mention instead of repeating them in the Args and Environment sections; this repetition costs it a perfect score.

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?

For an 8-parameter, zero-annotation tool with no schema-level descriptions, the description is highly complete. It specifies every parameter, returns a structured message (confirmation or error), gives lifecycle guidance, and enumerates environment prerequisites. It leaves nothing essential about how or when to call this tool, and the output schema covers the return payload.

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?

With schema description coverage at 0%, the description fully compensates by explaining not only what each of the 8 parameters does (open a URL, control headless mode, choose Chromium, specify an executable path, incognito, guest, ad-block, and proxy) but also the mutual exclusivity constraints (browser_executable_path not with use_chromium, and guest not with incognito). Real included conventions for proxy format and default headless behavior per OS, making each parameter actionable.

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 immediately states the core function with a specific verb and resource: 'Launch a persistent SeleniumBase Pure CDP Mode browser session.' It goes beyond a generic launch description by naming the browser-control layer (Pure CDP Mode) and explicitly positioning itself as the prerequisite for interaction tools like navigate, click, and type_text, which clearly differentiates it from those sibling tools.

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?

The description provides strong usage context: it must be called before browser interaction tools, should be called once at the start of a workflow, and close_browser should be called when finished. It also explains the session remains available across calls. However, it does not explicitly outline scenarios where starting a browser is not appropriate or compare itself to a non-browser alternative, leaving room for an explicit when-not-to-use statement.

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