Events Poll

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

With no annotations provided, the description carries the full burden and delivers: the return contract ({events, latest_seq}), the event categories, and cursor-based incremental semantics an agent cannot infer from the bare schema. It stops short of disclosing event ordering guarantees, retention limits, or whether the call blocks, but the core behavioral contract is well covered.

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 compact sentences with zero waste: the first front-loads the operation and scope, the second delivers the return contract and the canonical usage pattern. Every clause 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 2-parameter poll tool with an output schema present, the description covers the essential contract: input cursor semantics, output payload shape, event content types, and the recommended incremental loop. It is sufficient to call correctly; the absent details (ordering guarantees, event expiration) are minor for this tool's simplicity.

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 compensate. It gives real meaning to `since` — a seq cursor where events with seq > since are returned — which is significant added value. `limit` receives no explanation, though its name and default value (100) make its role largely inferable.

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 (拉取/poll), a precise resource (实时事件/real-time events), and the exact filter mechanism (seq > since). It enumerates the event content (player speech, dice, movement, including dice history), which positions it distinctly from siblings like chat_read and dice_roll.

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?

Explains the incremental polling workflow explicitly: store latest_seq from the response and feed it back as the next since parameter. However, it never states when to prefer this unified event stream over sibling alternatives such as chat_read, which plausibly serves the same 'read player speech' need, and names no exclusions.

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