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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=true): it discloses that the broadcast is pulled, the pin and visible replay interaction are removed, that the action is irreversible with no restore entry, that live-audience exposure cannot be undone, that it does not affect the account or other sessions, and that repeat calls keep it hidden. It also warns against automatic retry and directs verification via get_organizer_live on unknown results.

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-loads the actor/scope tag before the action, and nearly every clause carries operational weight (irreversibility, scope limits, idempotency, retry ban). It is a dense single block with several semicolon-joined clauses, slightly heavy to parse, but no sentence is wasted.

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 destructive, irreversible mutation with no output schema, the description supplies everything an agent needs: auth/role requirement, pre-verification workflow, reversibility and scope boundaries, idempotency behavior, and retry guidance. Nothing critical is left to inference.

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 liveId, messageId, and activityRef are already fully documented in the schema. The description reinforces that messageId should be verified against author/full text via get_organizer_live, but adds little semantic detail beyond what the schema provides, so the baseline of 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 (隐藏/hide) and a precisely scoped resource (本场互动消息/this session's live message). The bracket tag 【需登录·本场主办方】 immediately identifies the actor and scope, distinguishing it from sibling tools like pin_live_message, recall_my_message, and ban_live_user.

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 the actor requirement (organizer of this session, logged in), the prerequisite (verify author/messageId/full text at the host console and confirm first), and names the alternative verification tool get_organizer_live for unknown outcomes. It also states there is no un-hide/restore path, which steers the agent away from an action that does not exist.

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