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

Annotations cover only read-only and closed-world safety, but the description adds the delivery semantics that actually matter: at-least-once delivery with dedupe on event_id, 7-day retention and backlog caps, and a specific error code (410 cursor_expired) with a recovery path. This is context an agent cannot get from structured fields and is exactly what prevents duplicate processing.

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-loads the return semantics, then the dedupe rule, then the paging loop, then the failure mode — a natural execution order. Five short clauses with no filler; every sentence changes how the tool is called.

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 two-parameter polling tool with no output schema, the description supplies return shape (events identify arrivals by id), the paging and ack loop, idempotency handling, and the terminal error case with recovery. An agent can run the full loop correctly without further documentation.

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 0%, so the description must carry parameter meaning, and it explains `cursor` thoroughly (omit to continue from last ack, take next_cursor from the prior page). However, `limit` is never mentioned in the description despite having no default documented in the schema, so one of the two parameters remains semantically thin.

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 ('Returns the next events for this seat'), plus ordering ('oldest first') and the cursor-relative position. It also distinguishes the payload ('Each event names an arrival by id') and routes detail lookups to read(), so an agent can separate it from events_ack, events_subscribe, and read without opening any 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 explicit when-to and what-next guidance: omit cursor to continue from your last ack, pass next_cursor into the next call, ack the page with events_ack, and on cursor_expired resync through read() then events_subscribe with restart: true. Alternatives and the exact condition selecting each are named, leaving nothing to inference.

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