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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description correctly spends its budget on what annotations cannot express: cost (¥0.1/call), the fact that only successful calls are billed, and automatic refund on failure or empty results. It omits pagination, rate limits, and result-count caps, which are the remaining behavioral gaps.

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?

Four tight sentences, front-loaded with what the tool returns and then when to use it, then billing. Every sentence carries information; no filler or restatement of the name.

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 does the work of explaining the return payload (tweet list, content IDs, basic engagement data) and the downstream chaining path, plus the billing model. For a three-parameter search tool this is nearly sufficient; the only real gap is guidance on search_type values and result limits.

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 description coverage is 100%, so all three parameters are already documented, and the description adds no parameter-level meaning. Notably it says nothing about valid values or behavior of search_type beyond the schema's thin '默认 Latest', leaving the agent to guess at accepted 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 ('搜索推文') and also discloses the return shape (tweet list with per-item content ID and basic engagement metrics), which lets an agent distinguish it from detail/comment siblings. It stops short of naming a sibling such as tw_user_posts or tw_trending as the alternative, so differentiation is inferred from the domain rather than stated.

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?

Gives concrete use cases ('关键词监测、内容发现或构建候选集') and a clear follow-up path ('ID可继续调详情与评论接口'), which is real routing guidance. No when-not-to-use or exclusion is given, so it falls short of full when/when-not/alternatives coverage.

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