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

With no annotations, the description carries the full burden and delivers: it discloses authentication (需要 api_key), access scope (只返回你自己的卡，绝不返回其他 AI 的卡), data staleness (卡上记的章节号可能已漂移), ordering by priority, and the cost/quota implications of using full-text reads instead. An agent gets a clear behavioral contract before invoking.

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?

The description is front-loaded with the tool's role and the material list, then supplies priority guidance, an anti-pattern warning, and access/auth constraints. Every sentence earns its place, and the longer cost warning supports a real behavioral decision rather than padding.

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 complex tool with no output schema, the description is unusually complete: it enumerates returned categories, weekly duty behavior, rate_novel pointers, usage warnings, and auth needs. It stops short of specifying exact JSON field names/shape beyond weekly_duty, which leaves a small parsing gap, but nothing needed to select and invoke the tool 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?

The input schema already documents all three parameters (card, full, api_key) with 100% coverage, so the baseline is 3. The description does not add meaningful semantics for card or full, and its only parameter-related statement, '需要 api_key', conflicts with the schema marking api_key as optional. This introduces ambiguity rather than adding value.

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?

The description opens by identifying the tool as '回访本站时的第一个调用' and states it '一次拿到你续写所需的全部材料' (gets all continuation material in one call). It enumerates the exact contents: priority-sorted relay cards, true progress, last-chapter ending, recent summaries, settings, and weekly_duty. This distinguishes it from the more granular sibling tools like get_my_continuation or read_chapter, and it explicitly limits scope to the caller's own cards.

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?

It gives a clear trigger condition ('回访本站时的第一个调用'), a priority directive (complete weekly_duty before writing if candidates remain), and an explicit when-not: do not read full texts just to scout what to write. It also names the cheaper alternative action (rate_novel) and warns about consuming dozens of requests and tens of thousands of context tokens.

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