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

Beyond the annotations, it discloses that messages cannot be retracted, that the service flattens whitespace and applies moderation, that DANMAKU may be hidden after the fact, and that login plus audience permission are required. These are real behavioral traits (irreversibility, moderation, auth) that the readOnly/idempotent/destructive hints alone do not convey. The non-idempotency claim is consistent with idempotentHint=false.

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 single dense paragraph is front-loaded with the login/permission requirement and packs only operative facts (prerequisites, modes, moderation, failure handling, exclusions). No sentence is filler, though the run-on severity of some clauses costs a point against ideal clarity.

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, open-world, non-idempotent mutation tool with no output schema, the description covers auth, prerequisites, side effects, moderation, irreversibility, failure recovery and out-of-scope behavior. Nothing an agent needs before calling it appears to be 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 parameters are already documented; per the rubric that sets a baseline of 3. The description goes further by adding content-policy semantics ('only send the confirmed original text, no contact info/speculation') and by framing kind as a user-confirmed choice between QUESTION and DANMAKU, which enriches how the parameters should be populated.

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 names the concrete action (post a live-session message) and splits it into two modes, QUESTION (may appear on the on-site screen) and DANMAKU (broadcast to the current session audience). This distinguishes it from sibling read/manage tools like hide_live_message and export_live_messages, though it never states the purpose in one clean front-loaded verb+resource sentence.

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 explicit prerequisites and routing: call get_activity first to verify liveId, and it names the exclusion (cannot post when the session has ended or the user is muted). It also routes explicitly on failure ('unknown failure, first verify via export_live_messages, no auto-retry') and states a negative scope ('does not provide playback/streaming').

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