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

With no annotations, the description carries the full burden of behavioral disclosure, and it does so well. It explains the browser selection logic (foreground first, Chrome fallback), the return object, and the important side-effect that a non-null pageId makes the opened tab the current page for subsequent devtools calls. It doesn't mention error conditions or permissions, but the core behavioral traits are clearly communicated.

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 three sentences long, with the primary purpose stated first. The second sentence adds the browser-selection nuance, and the third explains the return value and follow-up usage. Each sentence carries useful information, though the third sentence is slightly dense and could be split for easier parsing. Overall, it's efficient and well-organized.

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 a tool with no output schema and no annotations, the description covers the essential details: what it does, browser fallback behavior, return values, and the pageId side-effect that affects subsequent tool calls. It doesn't explicitly address failure scenarios (e.g., invalid URL, no browser available) or permissions, but these are not critical for an agent to invoke the tool correctly in most cases.

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?

The input schema already covers both parameters (url and udid) with clear descriptions at 100% coverage. The tool description doesn't add new parameter-level semantics; it focuses on behavior and return values. Per the calibration rule, a baseline of 3 is appropriate when the schema handles parameter documentation fully.

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 opens with a clear, specific verb and resource: 'Open a URL in a browser on an Android device.' It further distinguishes itself from sibling tools by describing its foreground-browser behavior and Chrome fallback, making its role unambiguous even among many related navigation 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 practical context by explaining when this tool is the right choice: it's 'much simpler than manually tapping the address bar' and it drives the foreground browser, with a fallback to Chrome. It also explains how to continue working with android_devtools_* and webpage_* tools using the returned pageId. However, it doesn't explicitly name alternative tools or state when NOT to use it, leaving some inference to the agent.

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