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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, idempotentHint, openWorldHint), so this only needed additive context — and it delivers: the liveId default behavior, the fact that recent/pinned carry messageId, and the operational boundary that streaming credentials/URLs are out of Agent scope. Rate limits and the exact return shape of a session are not covered, keeping it short of a 5.

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?

Front-loaded with the auth/scope qualifier and the core action, and every clause carries routing or constraint information with no filler. The compression is heavy enough that it reads as telegraphic, which slightly hurts parseability, but nothing is wasted.

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 does partial duty on returns by noting the default-latest selection and the messageId present in recent/pinned. It does not describe what a live session record itself contains (status, timing, stream state), which for a read tool with no output schema is a remaining gap.

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%, so the baseline is 3; the description earns an uplift by adding semantics the schema omits — notably that liveId defaults to the latest session when absent. activityRef meaning is left entirely to the schema, which does document it adequately.

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 and resource ('读直播场次') scoped to the organizer with a stated auth requirement ('需要登录·主办方'). It explicitly differentiates itself from four siblings by name (export_live_messages, ensure_activity_live, start_live_session, end_live_session), so an agent can place it precisely in the live-session tool family.

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 explicit when-to-use routing: read sessions here, use export_live_messages for the full message set, ensure_activity_live when no session exists, start_live_session to go live, end_live_session to stop. It also states an important exclusion — stream keys and push/playback/replay URLs are not delivered through the Agent (OBS goes to the /pro console, viewers go to the App).

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