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

Beyond the annotations, the description discloses two important traits: the response is incremental with a cursor implied by 'since your last call', and the call blocks for up to timeout_seconds rather than returning immediately. This is real behavioral value not available from the annotations, and it is consistent with readOnlyHint=true and idempotentHint=false (each call consumes new events). It does not state whether events are drained/cleared or replayed.

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 sentences, both earning their place: the first defines the payload with a concrete example of an alert, the second defines the blocking semantics. The most decision-relevant information (what you get) is front-loaded.

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 carries the burden of explaining the return and does so adequately (chat, whispers, alerts). The blocking-timer behavior is covered. Minor gaps: whether events are consumed on read and what the response looks like when the timeout expires.

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% for the single parameter, so the baseline is 3. The description adds only a modest clarification — that timeout_seconds is an upper bound on how long the call blocks — which the schema's '0-25, default 15' does not spell out.

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 names the resource concretely: 'New chat and whispers since your last call, plus alerts (you died, a player is attacking you).' That distinguishes it from siblings like status or look_around by making clear it returns an event feed rather than a state snapshot, though it never names an alternative explicitly.

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?

Usage is implied by 'since your last call' — i.e. poll repeatedly to get incremental events — and the wait behavior is stated. However, there is no explicit guidance on when to prefer this over status/look_around, nor any advice on polling cadence or what to do when nothing arrives.

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