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

Annotations already declare readOnlyHint/destructiveHint=false, and the description still adds substantive behaviour beyond them: at-least-once delivery, gap-free per-workspace seq, retention overflow producing cursor_expired, and the fact that payload bodies are omitted. These are exactly the properties an agent needs to consume the stream correctly.

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 highest-value facts (cursor semantics, pointer-only payloads, long-poll) and no filler sentences; each clause carries operational meaning. The density is high but the paragraph lacks any visual grouping, making the filter behaviours easy to skim past.

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 present, return values need no explanation, and the description covers delivery guarantees, cursor lifecycle, and expiry recovery thoroughly. The remaining gap is semantic coverage of three filtering parameters, which matters for an 8-parameter tool with no schema descriptions.

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% across 8 parameters, so the description carries the full burden. It explains cursor, wait_seconds, types (prefix syntax like doc.*), for_me, and subscription_id semantics well, but leaves limit, namespaces, and written_by_subtree entirely undefined in both schema and prose.

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 opening sentence names the resource (events), the cursor-based scope, and the delivery shape (pointers only, no bodies) plus the long-poll window, which is far more specific than a restatement of the name. It stops short of an explicit verb like 'fetch/list' and does not differentiate itself from near neighbours such as workspace_sync or subscribe except in the expiry-recovery clause.

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?

It tells the agent exactly how to start (cursor=null begins at the current position with no replay), how to continue (pass next_cursor back each time), how to handle duplicates (dedupe by event_id), and what to do on failure (cursor_expired → resync with workspace_sync(since=null)). The alternative path is named explicitly with the condition that selects it.

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