auto_play

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

With no annotations provided, the description carries the full disclosure burden and does substantial work: it reveals the async non-blocking nature (立即返回), continuous background autonomy (自主的后台), and the full set of side effects it triggers (voting, chatting, settling, reward claiming). It stops short of disclosing that the loop persists until explicitly stopped and gives no error-handling or rate-limit context.

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 with zero waste: the first delivers the core purpose and action list, the second delivers the critical async caveat and the monitoring route. Key information is front-loaded and every word 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?

The description covers the essentials — what the loop does, that it returns immediately, and how to track progress — and the schema richly documents all six parameters. Gaps remain: with no output schema, it never states what the immediate return value contains, and it omits prerequisites (e.g., an active session/room) and the fact that the loop runs until stop_auto_play is called.

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 100%, with every parameter documenting its default, range, and behavioral effect (settleEnabled explicitly says it invokes settleRound; both enums spell out choices and defaults). The description itself adds no parameter-level meaning, which is acceptable under the high-coverage baseline.

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 (启动/start), a clear resource (自主的后台游戏循环/autonomous background game loop), and enumerates the concrete behaviors it performs (自动投票、聊天、结算轮次和领取奖励). The immediate-return note and the get_auto_play_status reference distinguish it from sibling tools like stop_auto_play and get_auto_play_status without ambiguity.

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 second sentence explicitly routes the agent to get_auto_play_status for monitoring after invoking this tool, establishing clear context for how the tool fits into the workflow. However, it does not state when to prefer this automation over the manual per-action siblings (action_onchain, settle_round, claim_reward) or give explicit when-not-to-use conditions.

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