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

Annotations declare destructive/idempotent/openWorld, and the description adds rich context beyond them: the action is irreversible (audience room closes immediately, session can never be reopened, a new session is required to broadcast again), repeat calls are a silent no-op, and hasRecord=false at end-time does not mean recording failed due to callback delay.

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?

Organized into 【何时用】【组合链】【口径/坑】 sections that are front-loaded and each sentence carries actionable content (login requirement, confirmation rule, chaining, three pitfalls). No filler despite the density.

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?

With no output schema, the description compensates by explaining the post-call verification step (re-read for hasRecord) and the callback-delay nuance. Auth requirement, irreversibility, and idempotency are all covered, so an agent has everything needed to call it correctly and safely.

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%, so liveId and activityRef are already documented in the schema. The description only indirectly references liveId via the get_organizer_live chaining step and adds no new parameter syntax or meaning. 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 makes clear this ends a live session (收场 / 结束这场直播), a specific verb+resource, and the name reinforces it. It does not explicitly name a sibling like start_live_session to differentiate, but the action is unambiguous.

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?

Gives an explicit usage scenario (broadcast finished, host on-site without a computer), a mandatory precondition (must confirm 'end this livestream now' with the user first), and an exact chaining recipe (get_organizer_live → this tool → re-read for hasRecord). Nothing is left to inference.

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