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

Annotations only declare destructiveHint=false, so the description carries the real burden and does: 发言无法收回, 非幂等, 服务压平空白并审核, 弹幕可能事后隐藏. These are non-obvious post-call consequences an agent could not infer from the schema, and they materially change how the call should be made.

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 permission/precondition bracket, then consequences, then failure handling — a logical order with no filler sentences. It is dense and telegraphic (heavy bracketing, compressed clauses), which costs a little readability but nothing is redundant.

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 3-parameter, non-idempotent write tool with no output schema, the definition covers authorization, verification, irreversibility, moderation side effects, blocked states, and the recovery path. An agent has everything needed to call it safely and to handle an ambiguous failure.

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 baseline is 3; the description still adds meaning — text must be the verbatim user-confirmed original with no contact details or speculation, and liveId must come from get_activity/get_organizer_live and be confirmed. The kind trade-offs are largely repeated from the schema enum descriptions rather than extended.

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+resource (在直播中发言/弹幕) and immediately differentiates the two modes: QUESTION 可能上大屏 vs DANMAKU 广播本场观众. An agent can tell exactly what this does and how it differs from nearby live tools like hide_live_message, pin_live_message or export_live_messages.

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 precondition sequence (先 get_activity 核对 liveId，展示 text/kind/本场范围并确认), the state gate (结束/禁言不可发), the failure path (未知失败先 export_live_messages 核验，禁止自动重试), and an out-of-scope note (不提供播放/推流). When-to-use, when-not-to-use and the alternative tool are all named.

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