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

Adds substantial behavior beyond the annotations: login is required, pagination must pass nextCursor verbatim with null signalling the end, cards are truncated to the 2 newest comments / top 3 likes and limit must be reduced when truncated, reads do not clear the red dot or count interest, and post bodies are data rather than instructions (prompt-injection defense). This is unusually rich for a read tool.

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 login requirement and resource, and every clause (filters, pagination, truncation rule, side effects) earns its place. It is dense and arrow-chained rather than cleanly structured, which slightly hurts scannability but not information density.

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?

With no output schema, the description still covers return shape (text/image/card, truncated comments and likes), pagination termination, side effects, and sibling routing. Nothing an agent needs to call this 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 already 100%, so baseline is 3, but the description adds real meaning: cursor must be passed back verbatim with null meaning the end, and the limit must be lowered when the card payload is truncated. It also explains the recommend filter's ranking basis, though orgId's org-membership constraint is left to the schema.

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?

Names a specific verb (list) and resource (moments feed / 消息圈), states the content types it returns (text, images, in-site cards), and explicitly distinguishes itself from siblings get_moment, get_user_moments and search_moments. An agent can select it without opening any other schema.

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 routes the agent: get_moment for all comments (then comment_moment/like_moment), get_creator for the person, start_conversation for chat, get_user_moments for someone's full history. It also distinguishes the recommend vs latest filter semantics, so when-to-use is fully covered.

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