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

Annotations only declare destructiveHint=false, so the description carries the behavioral load and does it well: per-author aggregation with a 6-item cap, primary-first ordering, a logged-in re-ranking by the viewer's own canOffer, and the non-obvious cursor semantics (cursor continues the same batch, omitting it re-sorts). The disclaimer that listings carry no quota or reward commitment is a genuinely useful data caveat that cannot be inferred from any structured field.

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 what the feed is, then ordering rules, then pagination caveat, then the workflow chain — no filler sentences. The telegraphic semicolon-and-arrow style is efficient but somewhat cryptic for readers unfamiliar with the domain shorthand.

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 read tool with minimal annotations and no output schema, it covers ordering, aggregation limits, pagination stability, data caveats, and the follow-up call chain. The main remaining gap is the shape of a returned feed item beyond need.id, which an agent must discover by calling.

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 baseline is 3; the description still adds real meaning for cursor by explaining that it resumes the same batch while omission triggers a re-sort — behavior the schema's '原样回传' does not convey. It adds nothing for type or limit beyond the schema, which already enumerates the eight need types.

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 and resource — aggregates active (在架) needs by author, capped at 6 per person, primary items first. It also names the sibling it is not (search_needs for targeted lookup), so an agent can distinguish feed browsing from search without opening either 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?

Explicit routing: use this feed for browsing, use search_needs for targeted queries, and update_my_profile(canOffer) when the caller's self-description is insufficient to get good ranking. It also lays out the downstream chain need.id→get_need→contact_need→send_message, giving the agent a complete when/when-not map.

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