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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavior beyond them: newest-first ordering, page-level pagination via next_offset (null when complete), the SCREEN_PAGES_FULL refusal condition at pages_limit, and the auto_delete eviction rule. It also clarifies that pages_used counts pages_from_others, which is non-obvious semantics an agent could not get from 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 purpose is front-loaded, but the whole definition is one long semicolon-chained sentence mixing return fields, limits, eviction policy, pagination, and applicability. The enumerated return fields (view_id, revision, title, ...) duplicate the output schema, so they add bulk without adding information.

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 read-only two-parameter lister, the description covers ordering, pagination, capacity failure modes, and where the tool is supported, which is enough to call it correctly. The remaining gap is the undocumented "device" parameter, and the field enumeration is redundant given an output schema exists.

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 0%, so the description must carry both parameters. It explains offset indirectly ("next_offset ... is the offset that continues it"), which is genuinely useful, but never explains what "device" accepts — an ID, a name, or the screen reference — leaving the required parameter undocumented anywhere.

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 gives a specific verb and resource ("Lists the pages a phone-owned screen keeps") and narrows scope to what "this connection's sender sent", explicitly noting that pages from other apps/accounts appear only in the screen's Settings › Page history. That scope boundary functions as differentiation, though no sibling tool (e.g. page_show, page_delete) is named as an alternative.

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?

Usage is only implied: the text states the tool "Works where the screen's support lists it (phone-owned screens with a current app)", which is a precondition rather than a when-to-use rule. It never says when to call this instead of page_show or view_get_state, leaving the agent to infer the selection.

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