讀取已收到的事件

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

Beyond the readOnlyHint annotation, the description explains meaningful behavior: continuous reading via nextCursor, buffer wrap-around detection via dropped, and the implication that events may be permanently lost if dropped > 0. It also explicitly states '無副作用' (no side effects), which aligns with and reinforces the readOnlyHint annotation.

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?

The description is three concise sentences with no filler. It front-loads the core action, then provides the essential cursor usage, and ends with the important dropped warning. Every sentence earns its place.

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 polling tool with an output schema, the description provides enough context to use it correctly: initial cursor, continuation pattern, and failure signal. The remaining parameter details are present in the input schema, and the output schema covers return values. No critical operational context is missing.

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 schema description coverage is only 33%, so the description must compensate. It does explain afterCursor semantics well, including the first-call value and nextCursor continuation. However, it does not describe the limit parameter, and eventName is already covered by the schema. This is adequate but leaves one parameter's semantics to the schema's default and range constraints.

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 clearly states the tool's function: '取出游標之後的事件' (retrieve events after a cursor). It uses a specific verb and resource and is distinct from sibling tools like mc_events_catalog, mc_events_subscribe, and mc_events_unsubscribe by focusing on polling/reading already-received events.

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 gives concrete usage instructions: use afterCursor=0 for the first call and pass the returned nextCursor thereafter. It also explains how to interpret the dropped indicator. It does not explicitly mention when to prefer this over sibling tools, but the cursor-based polling pattern is clearly conveyed.

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