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

With no annotations present, the description carries the full disclosure burden, and it goes far beyond typical descriptions. It explains trusted vs. synthesized events, focus behavior, iOS fallback mechanics, form submission handling, and the response's `via` field—genuinely valuable behavioral context.

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 core purpose is front-loaded, but the remaining content is a dense single-sentence block. Every detail is relevant and valuable, though the structure could be improved with clearer shorter sentences or bullet points. The length is justified by the complexity, so it remains effective.

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 annotations and no output schema, the description thoroughly covers platform differences, fallback behavior, focus consequences, and response reporting. It does not mention prerequisites (e.g., an already-open browser page) or failure conditions, but the essential behavior needed to invoke and interpret the tool is comprehensively documented.

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 provides descriptions for 100% of the parameters, so the baseline is 3. The description adds contextual nuance for the `key` parameter (e.g., Enter inside a form triggers submission), but it does not elaborate on udid, pageId, socket, or platformVersion beyond what the schema already states.

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 verb+resource ('Press a key in the device browser') and immediately scopes it to iOS Safari and Android Chrome, which distinguishes it from sibling tools like web_press_key or device_key. The platform-specific scope makes the tool's role unmistakable.

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 implies the intended context (device browser on iOS/Android) and details platform behavior, but it never explicitly names alternatives or says when not to use this tool. An agent would have to infer the selection criteria from the platform mention rather than being told outright.

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