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

Beyond the supplied idempotentHint/destructiveHint, it explains what idempotency means in practice (late callbacks won't re-announce) and adds a crucial caveat that the tool only changes status and does not prove video is actually flowing, requiring the organizer to verify by eye. This is exactly the kind of behavioral context annotations cannot express.

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 but front-loaded with the core fallback scenario and no wasted sentences; every clause carries signal. The telegraphic semicolon-separated style (and the stray leading '登录') slightly hurts readability but not substance.

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 2-param mutation tool with no output schema, it covers purpose, sequencing, idempotency behavior, verification caveat, and the terminal error state (live_ended). Nothing an agent needs to call it correctly is missing.

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 both params (liveId, activityRef) are already documented with their sources. The description reinforces where liveId comes from via the get_organizer_live step but adds no new syntax or meaning for activityRef, 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?

States a specific action (manual set to LIVE) with a precise condition: streaming has begun but the callback was lost and viewers still see not-live. It also distinguishes itself from siblings by naming get_organizer_live as the pre-check and end_live_session's territory via 'live_ended, create a new session only.'

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 ordered workflow: get_organizer_live confirms IDLE → this tool → read back LIVE, so the agent knows when and how to sequence it. It also states the exclusion (if already ended, report live_ended and create a new session instead) so the boundary against alternatives is clear.

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