What changed since you last looked

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-redundant behavior: events form a contiguous run, are returned oldest-first as whole events (actor, item id, fields), include user edits made in the widget that never pass through the agent, and carry `next_since` for continuation.

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 purpose, and the paragraph packs purpose, mark sources, return shape, and continuation without filler. It is dense enough that the continuation detail sits mid-sentence rather than being broken out, but nothing is wasted.

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?

With an output schema and rich annotations present, the description only needs to add mechanism, and it does: mark provenance, ordering, event contents, and pagination continuation. It omits failure/edge behavior (e.g. what happens if `since` is older than retained history), which is the one gap for a paging read tool.

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 67% (`collection` is undocumented in the schema), and the description compensates for the most ambiguous parameter by explaining that `since` accepts several mark formats and what omitting it means. `limit` adds nothing beyond the schema, and `collection` is still only implied.

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+resource+scope: report what changed in a collection after a ledger position the caller holds, including widget-side edits. It distinguishes itself from generic reads by naming the ledger-position mechanism, but it never names the closest sibling (get_data_version), which is the tool an agent would most likely confuse it with.

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 triggering context: pass any mark you hold (write ack's `seq`, data_list's `version`, last call's `next_since`) as `since`, and omit `since` to just learn the current position. It does not state when to prefer get_data_version instead, so one routing question is left to inference.

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