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

The description extensively documents behavioral traits despite no annotations being provided. It explains verification behavior (scopes verified by re-reading with before/after counts), platform-specific differences (iOS removes cookies via Web Inspector reaching HttpOnly; Android uses Network.clearBrowserCookies), HTTP cache treatment (cleared on Android but unsupported on iOS), and the limitation regarding HTTP Basic Auth credentials. This fully compensates for missing annotations.

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 comprehensive but somewhat lengthy (about 15 sentences). It is front-loaded with the core purpose, which is good, but the latter portion dives into platform-specific implementation details that, while valuable, could be more terse. Every sentence adds information, but the verbosity slightly reduces scanning efficiency for the agent.

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?

The description is remarkably complete given the tool complexity (4 parameters, 2 platforms, 5 scopes, no output schema). It covers what gets cleared, verification guarantees, platform differences, edge cases (Basic Auth), and how it differs from sibling tools. Without an output schema, the description compensates by describing the result (before/after counts, unsupported scopes reported). No gaps remain for effective tool selection and invocation.

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 the schema already documents all 4 parameters. The description adds value by explaining the meaning of 'all' (all scopes the platform supports) and the default value (['all']). However, it does not add detail beyond what the schema provides for udid, pageId, or socket, though the action-specific behavior is well covered.

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 clearly states it clears multiple web storage types (cookies, localStorage, sessionStorage, cache) and specifies the device browsers (iOS Safari, Android Chrome). It distinguishes itself from sibling tools like webpage_reload (which preserves localStorage) and webpage_clear_cookies (which only handles cookies). The verb 'clear' plus explicit resource scopes provides an unambiguous purpose.

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 explicitly states when to use this tool: 'get a genuinely clean session between test cases'. It contrasts with webpage_reload which 'deliberately PRESERVES localStorage', and notes that webpage_clear_browsing_data is needed to clear state that reload retains. It also warns about HTTP Basic Auth, directing users to ios_terminate_app instead. This provides clear when-to-use and when-not-to guidance.

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