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

Even with annotations marking destructiveHint and idempotentHint, the description adds concrete behavioral teeth: the viewer room closes immediately, the action cannot be undone, repeated calls are silent no-ops, and hasRecord=false at close time is not evidence of recording failure. This is exactly the kind of context annotations cannot convey.

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 compact, sectioned with clear labels (需要登录/何时用/组合链/口径/坑), and every clause carries operational value. No filler or redundant restatement of the schema.

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?

Despite having no output schema, the description covers login, when to invoke, the prerequisite confirmation, the composition chain, irreversibility, idempotence, and post-close recording semantics. An agent has everything needed to decide and call it correctly.

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% and both parameters already carry clear provenance descriptions (liveId from get_organizer_live; activityRef from get_activity/get_signup_activity). The description restates the chain but adds little semantic value beyond the schema, so the baseline 3 applies.

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's opening '何时用' plus '收场' and '结束这场直播' makes clear this tool permanently ends an organizer's live session. The chain references get_organizer_live and contrasts with the obvious sibling start_live_session, so an agent can distinguish it without opening schemas.

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?

It explicitly states when to use it ('播完了，主持人人在现场手上没电脑'), the mandatory user-confirmation precondition, and the recommended chain (get_organizer_live → this tool → later re-read for hasRecord). The '播完了' condition also implies not to use it while the live is still intended to continue.

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