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

Annotations already declare readOnly/idempotent/openWorld, but the description adds substantial behavior beyond them: hidden and mutually-blocked messages are excluded, pagination defaults (1000, max 2000) with reachingLimit/nextSinceOffsetMs continuation, and a same-millisecond boundary gap that can drop items. That caveat is exactly the kind of non-obvious trait structured fields cannot convey.

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?

Very information-dense and front-loaded with the login prerequisite; essentially every clause carries a fact. It is a single run-on block that is slightly hard to parse, but there is little wasted content.

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 read-only export tool with no output schema, the description covers the permission model, pagination mechanics, edge-case data loss, and the alternative write path. An agent has enough to call it correctly and interpret reachingLimit without extra fields.

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 the 3 baseline applies, but the description goes further by explaining offsetMs as a paging offset, clarifying kind=QUESTION semantics, and restating the limit default/cap and the reachingLimit continuation field. These add practical usage meaning beyond the schema text.

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 (导出/export) and resource (互动时间轴/interaction timeline) scoped to the caller's audience permission, and names the mode switch via kind=QUESTION. It also routes the agent to post_live_message for the write path, distinguishing itself from sibling live-message tools.

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?

Explicit when/when-not guidance: login required, public activities readable when logged in, private require membership/invite, and a 404 cannot be worked around with join_activity_online. It also names get_activity/get_organizer_live as sources for liveId and post_live_message as the alternative for posting.

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