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

Annotations only declare readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description adds meaningful behavior beyond that: which browser engine is used, that it is isolated from the app, that a snapshot is produced, and the exact failure mode (host_not_allowed) with its default private-range blocklist. It stops short of covering navigation timing, timeouts, or what the snapshot contains.

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?

Two sentences, zero filler, with the core action and its isolation property front-loaded and the host-restriction caveat immediately after. The inline enumeration of blocked ranges is dense but earns its place by preventing a predictable error.

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?

With no output schema, the description correctly signals that a snapshot is returned, and it preempts the most likely failure (private host refusal) for a 4-parameter open-world browser tool. An agent has enough to call it correctly on the first attempt.

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 coverage is 100%, so baseline is 3, but the description goes further by explaining the default private-host policy and that an opt-in exists, which gives real meaning to allow_private and allow_hosts beyond their terse schema strings. The session parameter's dependency on open_app is left to the schema.

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?

States a specific verb and resource ('Open a web page in the phone's Chromium') and adds the distinguishing detail that Chromium runs separately from the app, plus that a snapshot is returned. It does not explicitly differentiate itself from close siblings like open_url or browser_snapshot, so it falls short of a 5.

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 second sentence gives actionable guidance about private-host refusal and the opt-in escape hatch, which is real when-to-use context for allow_private/allow_hosts. However, there is no guidance on when to pick this over open_url or when to follow up with browser_snapshot/browser_click, so usage against siblings is only implied.

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