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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds genuinely non-obvious behavior: a page can hold fewer than `limit` events because of filtering. That pagination caveat is real value beyond the 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?

Three tight sentences with the core behavior front-loaded. The leading repetition of the title 'Replay events' is the only wasted tokens.

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 no output schema, the description partially compensates by naming the `hasMore` and `lastSeq` response fields used to drive pagination, which is exactly what an agent needs to iterate correctly. The lingering afterSeq-vs-lastSeq naming ambiguity is the only gap.

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 100%, so `type`, `limit`, and `afterSeq` are already fully documented and the baseline is 3. The description adds the sequence-ordering guarantee but no new format/syntax detail, and it references a `lastSeq` field that does not match the schema's `afterSeq` cursor.

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 states a specific verb+resource ('Reads events in sequence order'), which is clearer than the tautological title 'Replay events'. No sibling tool covers events, so there is no differentiation problem to solve, but also no explicit scoping against the rest of the API surface.

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?

Pagination usage is implied ('continue from `lastSeq` while `hasMore` is true'), but there is no explicit when-to-use/when-not guidance or mention of alternatives such as polling vs webhooks. The guidance is functional but partial.

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