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

Beyond the annotations, it discloses login requirement, idempotency details (a later callback repeats the same set without duplicate broadcast), and a critical caveat: setting status does not guarantee actual video, so the organizer must visually confirm. It also notes the ended-session limitation, which is not captured in the annotations.

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 front-loaded with need, timing, sequence, and caveats in clearly marked blocks. Every sentence carries actionable information, and there is no filler or repetition.

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 mutation tool with no output schema and complete parameter documentation, the description covers login prerequisites, the exact workflow, idempotency, a major caveat about status vs. actual stream, and ineligible session states. An agent has everything needed to call and verify the tool 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 both liveId and activityRef are already documented in the input schema. The description adds sequencing context but does not clarify parameter formats, sources, or edge cases beyond what the schema provides, so the baseline of 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 states a specific action ('手工开播') and the exact scenario it addresses: streamer is already pushing but viewers see no live due to a lost callback. It also names get_organizer_live as the related read tool, making it distinguishable from siblings like ensure_activity_live or end_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 an explicit when-to-use condition ('推流机器已经在推，但观众端还显示没开播') and a full sequence: get_organizer_live status is IDLE → call this tool → re-read to confirm LIVE. It also states when not to use it: already-ended sessions cannot be opened and require a new event.

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