novel_delete_book

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

With no annotations, the description carries the full burden and does: it discloses that deletion is a two-step preview/apply flow, that data goes to trash/ under the data directory by default, that restore returns it intact, that purge is irreversible, and precisely which directories are untouched. This is exactly the safety context an agent needs before a destructive call.

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 default-preview warning and the apply gate, which are the highest-risk facts. The long parenthetical enumeration of artifact types (伏笔/设定表/摘要/必用词表/...) is somewhat dense but does earn its place by telling the agent what data loss to expect.

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 destructive multi-mode tool with no annotations and no output schema, the description covers modes, defaults, partial-selection semantics, trash lifecycle, and scope exclusions. Nothing material for correct invocation 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 100%, so baseline is 3; the description adds real value by explaining that omitted `keys` means 'select all, i.e. delete the whole book' and that keys come from preview's targets[].key, which the schema only hints at. The action enum semantics are largely duplicated from the schema, keeping this below a 5.

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 (delete/clean up by book) and enumerates exactly what is removed: body text, creation materials, setting-library entries, and associated artifacts. It also scopes the deletion to a single book, explicitly excluding global word lists, plugin settings, event logs, and other books' files, which no sibling tool does.

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 states the default mode (preview, no disk writes) and the condition for real deletion (action:"apply"), plus the partial-cleanup path via `keys` with a concrete example (only clearing reports and cache while keeping the body text). It also names the restore/purge alternatives and their irreversibility, leaving nothing to inference.

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