訂閱遊戲事件

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

The description adds meaningful behavior beyond the annotations: events are stored in a ring buffer, consumed via mc_events_poll, and subscriptions are automatically re-established after reconnection. This complements the idempotentHint annotation without contradicting it.

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 concise sentences cover the purpose, behavior, follow-up operation, and reconnection semantics without redundancy. The most important information is front-loaded with clear examples.

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 single-parameter subscription tool with an output schema and annotations, the description covers the key aspects: what to pass, what happens to events, how they are retrieved, and reconnection behavior. It does not mention the event catalog, but sibling naming makes that discoverable.

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?

The input schema provides no description for eventName and schema description coverage is 0%. The description partially compensates by giving examples of valid event types, but it does not specify where to find the complete list of event names or whether the value must match an exact catalog entry.

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 action (開始接收 / subscribe) targeting a specific resource (某類遊戲事件), with concrete examples like PlayerMessage, BlockPlaced, and PlayerTravelled. It clearly distinguishes this tool from the sibling poll tool by explaining the ring-buffer flow.

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 provides clear usage context: subscribe first, then retrieve events with mc_events_poll. It explains the purpose as letting the AI perceive player actions. It does not explicitly mention alternatives like mc_events_catalog or mc_events_unsubscribe, but the flow with mc_events_poll is explicit enough.

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