Retrieve recent visual novel lines and recorded choices for a player agent to review context, recall decisions, or recover progress before continuing.
Backlog of recent lines and choices made. / 回想
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | ||
| book | No | 书的 slug（见 galbook_books）。服务端设了默认书时可省略 | |
| agent | No | 你的玩家名（1-40 位字母数字/中日文/_-.）。服务端设了默认名时可省略 |
Changes observed during successful MCP inspections.
v1.2.6Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. "Backlog" implies a read-only retrieval, but the description does not confirm read-only behavior, state whether results are scoped to a book or agent, explain default behavior when book or agent is omitted, or mention the 300-line cap.
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 short and front-loaded, and the bilingual "回想" adds a compact gloss rather than a long explanation. However, its brevity comes at the cost of under-specification for a three-parameter retrieval tool.
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 tool with no annotations, no output schema, three parameters, and no required fields, the description is too sparse. It does not explain the return shape, ordering, default book/agent resolution, or how n changes the result, leaving the agent to infer critical behavior.
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 description adds no parameter-level meaning beyond the schema, and the n parameter has no schema description at all. With only 67% schema coverage, the description should clarify that n controls the number of recent lines returned and explain how the optional book and agent defaults work, but it does neither.
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 phrase "Backlog of recent lines and choices made" identifies the resource as recent interaction history, so the agent can infer it retrieves a log. However, the verb is only implied through a noun phrase, and there is no explicit differentiation from sibling tools such as galbook_status, galbook_saves, or galbook_next.
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?
The description gives no guidance on when to call this tool versus alternatives like galbook_status or galbook_saves. It also does not mention defaults, prerequisites, or the practical situation in which a recent-history backlog is useful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.