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

Beyond the annotations (idempotentHint, readOnlyHint=false, openWorldHint), the description discloses rich behavior: existing sessions return created=false and are NOT modified (closed state untouched), true creation returns created=true AND flips onlineEnabled, and liveId=null signals non-official/unconfigured with an explicit no-retry instruction. This is exactly the extra context annotations cannot carry.

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?

Dense and information-loaded, but front-loads the core action and idempotency claim before the routing and edge-case clauses. Every clause carries distinct, actionable detail; only the breadth of content keeps it from being maximally tight.

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 still explains the return contract (created=true/false, liveId=null), the side effect on onlineEnabled, the no-retry rule, and the related tools for status, OBS key, and broadcasting. An agent has everything needed to invoke and interpret the result 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% and the single activityRef parameter is fully documented in the schema (slug or id). The description adds no syntax or format detail about activityRef, so it does not go beyond the structured field. Baseline 3 is appropriate.

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 (idempotently ensure/create a live session for this activity) and immediately distinguishes itself from siblings by naming update_organizer_ticketing for reopening and start_live_session as a fallback for broadcasting. An agent can tell exactly what this tool does versus the nearby live-session tools.

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?

Explicitly states prerequisites ('先确认开直播' – first confirm live is enabled), the alternative for the reopen case ('重开用update_organizer_ticketing'), the fallback tool (start_live_session), and a do-not-retry condition when liveId=null. This is full when/when-not/alternative routing.

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