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

Annotations cover the safety profile (destructiveHint true, idempotent, openWorld), and the description adds substantial context beyond them: per-scope verification by re-reading with before/after counts, platform-specific mechanisms (Page.deleteCookie one-at-a-time on iOS reaching HttpOnly cookies vs Network.clearBrowserCookies on Android), HTTP cache cleared only on Android with iOS reported unsupported rather than silently skipped, and the Basic-auth credential-store caveat with real evidence.

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 action and the reload contrast are front-loaded, and despite its length every sentence carries distinct operational value (verification semantics, platform differences, unsupported cases, auth caveat). It is dense rather than padded, though the volume of detail is close to the ceiling for a tool description.

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?

This is a destructive, cross-platform tool with no output schema, yet the description explains the return shape (before/after counts, unsupported scopes reported), platform behavior differences, and a non-obvious limitation about Basic auth. An agent has everything needed to invoke and interpret it correctly.

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 description coverage is 100% and every parameter (udid, pageId, scopes, socket) is already documented in-schema, so the baseline is 3. The description reinforces scopes ('every scope is VERIFIED') and the default-all behavior but adds no enum or format detail beyond 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 (Clear) plus the exact scopes it operates on (cookies, localStorage, sessionStorage, Cache Storage API) scoped to 'the page in the device browser'. It names platforms and auto-detection, and implicitly differentiates itself from the narrower sibling webpage_clear_cookies. An agent can identify the resource and action without opening the 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?

Gives an explicit when-to-use ('get a genuinely clean session between test cases') and names the alternative it is contrasted with: webpage_reload, which deliberately PRESERVES localStorage and keeps you logged in. It also states a critical boundary — it does NOT log out of HTTP Basic auth — and tells the agent the workaround (terminate Safari and navigate afresh).

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