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

Annotations already declare the write-but-non-destructive, idempotent profile, so the bar is lower; the description still adds genuine context beyond them by disclosing monotonic forward-only semantics ('an older cursor changes nothing') and per-seat scoping of the stored mark. It stops short of saying what happens with an unknown or malformed cursor.

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?

Two short sentences, front-loaded with the action and effect, with the resume consequence stated before the monotonicity caveat. No redundant restatement of the name or title.

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 one-parameter, non-destructive, idempotent write with no output schema, this covers what an agent needs: where the value comes from, what it changes, and that regressions are ignored. Minor gap is the error behavior for invalid or foreign cursors and whether other seats are affected.

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 the parameter meaning — and it does, explaining that `cursor` is 'a next_cursor you received' from the events stream rather than an arbitrary string. The constraint details (min/max length, required, no additional properties) remain in the schema.

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 ('Stores `cursor` as this seat's high-water mark') and immediately ties the effect to the observable outcome for the sibling tool events_list. An agent can distinguish this from events_list and events_subscribe 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?

The description makes the trigger clear: take a next_cursor you received and acknowledge it so a subsequent cursorless events_list resumes after it. It names the related read tool, but does not explicitly state when *not* to acknowledge (e.g., before processing events) or discuss alternatives such as events_subscribe.

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