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

Beyond the generic annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), it discloses real behavioral facts: iOS actions error rather than silently no-op, Safari can list/drive but not open/close, and no switching is needed because pageId targets a tab directly. It stops short of describing what an Android-side error looks like or limits on concurrent tabs.

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 platform-capability constraint is front-loaded and each sentence carries information, but phrasing like 'one tool for what would otherwise be several' and 'rather than pretending' is rhetorical padding that could be trimmed without losing meaning.

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 6-parameter, cross-platform tool with no output schema, it covers the platform matrix, the pageId flow, and the default action, which is what an agent needs to call it correctly. The Android-only 'socket' parameter is left entirely to the schema, a minor gap given how prominent it is in the signature.

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 already 100%, so the baseline is 3. The description still adds cross-tool meaning for pageId ('pass that pageId to any other webpage_* tool to act on that specific tab, on either platform'), which the schema field description does not convey.

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 names specific verbs and resource ('List, open, switch and close browser tabs on the device') and immediately frames scope against siblings ('one tool for what would otherwise be several'). An agent can distinguish it from ios_safari_list_pages, android_devtools_list_pages and webpage_close without opening any 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 states exactly which actions work on which platform ('list works on BOTH iOS Safari and Android Chrome', 'new, select and close are ANDROID ONLY'), explains the failure mode, and tells the agent how to route pageId into other webpage_* tools. It even advises on lifecycle hygiene ('close what you are done with').

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