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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false. The description adds genuinely useful context beyond them: the returned pageId is a required handle for every other web_* tool, and the surface is a desktop browser on a testing grid. It does not cover lifecycle details such as needing web_close or per-session page limits.

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?

Three compact clauses, with the desktop-vs-device distinction front-loaded before the alternative routing. The capitalized emphasis is slightly redundant against the later 'ON A REAL DEVICE' phrasing, but nothing is wasted.

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?

There is no output schema, yet the description still explains the key return value (pageId) and how downstream web_* tools depend on it. What remains unstated—cleanup via web_close, whether pages persist across calls—is minor for a two-parameter navigation entry point.

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 description coverage is 100%, with url and browser both documented including the browser choices and default. The description adds no format or syntax detail for these parameters, so the baseline 3 applies; the pageId mention is a return-value trait, not an input parameter trait.

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 states a concrete verb and resource (opens a page and navigates to a URL) plus the artifact it produces (a pageId). It explicitly distinguishes itself from the webpage_* family, so an agent can tell it apart from siblings without opening a schema.

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?

It names the alternative family (webpage_* tools) and the exact selecting condition (driving a browser on a real device, identified by a udid) versus this desktop/browser-grid tool. Both the when and the when-not are stated explicitly.

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