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

Annotations supply only idempotentHint=true, which the description usefully reinforces with '已结束重调no-op'. Beyond that, the description adds substantial behavioral context: the end is irreversible, the viewer room closes immediately, the same session cannot be reopened, and a new session is required to broadcast again. With only one annotation present, the bar is higher and a 3 reflects that the description still leaves the authorization boundary (only 'login' is mentioned, not host-ownership failure modes) and the exact response shape unexplained.

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?

Every clause carries operational information -- login, prerequisite check, confirmation, irreversibility, idempotency, replay timing -- with no filler. The telegraphic semicolon-chained style and abbreviations like '核回放' make it slightly dense to parse, which is why it falls short of 5.

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 destructive, irreversible action with no output schema, the description covers everything an agent needs: authorization entry (login), pre-verification, human confirmation, consequence of ending (viewer room closes, no reopen), idempotent retry behavior, and how to check recording/replay later including the delayed-callback pitfall. The only soft spot is that it does not say which tool exposes hasRecord, but the context is sufficient to act 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 description coverage is 100%, so baseline is 3. The description implies session verification via get_organizer_live, which lightly reinforces liveId's origin already stated in the schema ('来自 get_organizer_live'), but it adds no new detail about activityRef or format 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 conveys a specific operation on a specific resource: it references checking a live session and then ending it immediately ('必须获用户明确确认立即结束'), paired with the title '主办方：收场'. Combined with the name end_live_session and the named prerequisite get_organizer_live, it is distinguishable from start_live_session and get_organizer_live. It loses a point because the purpose statement is not front-loaded -- the text opens with '登录' (login) rather than stating 'ends the live session'.

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 gives concrete workflow guidance: log in, call get_organizer_live first to verify the session ('先get_organizer_live核对场次'), and require explicit user confirmation before ending. It also clarifies the repeat-call case ('已结束重调no-op'), which pre-empts a common mistaken retry. There is no explicit when-not-to-use or named alternative, which keeps it below a 5.

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