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

With no annotations provided, the description carries the full burden and excels. It discloses that index is positional and unstable, that iOS shows one tab at a time, that state confirmation costs a bounded parallel check per page, that 'unresponsive' could mean device asleep or a dialog is open, and that the call 'never fails the whole call just because nothing is in the foreground.' These are non-obvious behavioral traits that significantly help the agent reason about outcomes.

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 long but each sentence earns its place. It front-loads the purpose, then systematically explains return fields, state values, usage implications, and prerequisites. The structure flows naturally from what → why → how, with no fluff. The length is justified by the tool's complexity.

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?

Given there is no output schema, the description must fully explain the return structure and edge cases. It delivers the full list of fields, defines each state, explains the active-tab model, distinguishes pageId from index, mentions the Web Inspector requirement, and clarifies fallback behavior. This is everything an agent needs to correctly interpret results and decide next actions.

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 two parameters (udid, platformVersion) are already fully described in the schema with 100% coverage. The description does not add new input-parameter semantics—it focuses on output and behavioral context. Per the scoring rule, baseline 3 applies when schema covers parameters; no further compensation is needed but none is added.

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+resource: 'List inspectable Safari pages on an iOS device via the Web Inspector CDP bridge.' It enumerates the exact return fields (index, pageId, url, etc.) and adds a top-level currentActiveTab, and distinguishes itself from sibling page-listing tools by focusing on iOS Web Inspector semantics. This is unambiguous and distinguishes from android_devtools_list_pages or webpage_tabs.

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 explicitly explains when this tool is needed and when it isn't: 'you do NOT need to list pages and thread an id just to act on the current tab, only to target a DIFFERENT one.' It also describes the meanings of each state ('foreground', 'background', 'unresponsive', 'unprobed') and leaves clear guidance on how to handle each, including when to pass pageId explicitly and when to take a screenshot to disambiguate. This is textbook-level usage guidance.

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