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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds substantial behavior: reads are non-consuming, results are bounded, view/revision attribution is retained, event support varies by route, and gaps may include events from other pages even when view_id is set. The recovery_contract clause explains what 'recovery_lost' gaps mean after storage recovery, which is context no annotation conveys.

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?

Front-loaded with the core action and then organized by concern (cursor, defaults, gaps, pagination, recovery), and each sentence carries information. It is dense and jargon-heavy in places ('verified gaps', 'recovery_contract ais.recovery.v0'), trading readability for precision.

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 tool with an output schema, the description covers what an agent needs to call it correctly: cursor semantics, the null view_id default, the pagination continuation value, and the gap caveat that results may span other pages. The only remaining ambiguity, the meaning of device/limit/types, is narrow relative to the substantial coverage elsewhere.

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?

With 0% schema description coverage the description carries the full burden, and it explains after (numeric cursor), view_id (null = current remote view), include_screen_history_gaps (events plus verified gaps), and recovery_contract (ais.recovery.v0 enables recovery_lost gaps). device, limit, and types are left entirely undefined in both schema and description, which is a real gap for a 7-parameter tool.

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 and resource ('Reads ordered, non-consuming page interactions') plus the ordering key ('after a numeric cursor'), which is far more precise than the tool name alone. 'Non-consuming' and the view/revision attribution distinguish it from a state-reader sibling like view_get_state.

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 concrete usage conditions: null view_id selects the current remote view, include_screen_history_gaps switches to the gap-returning mode, and has_more/next_cursor defines the pagination loop. It does not name an alternative tool or say when not to use this one, so it falls short of explicit routing guidance.

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