novel_sentence_analysis

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

No annotations are provided, so the description carries the full behavioral burden — it discloses two non-obvious traits: shared engine/cache with its siblings (cached results may be served across tools) and availability gated by a UI switch. The schema's fresh parameter hints at caching, but the description adds the shared-cache and configuration-gating facts beyond the schema. It stops short of describing return shape or failure conditions, which keeps this from a 5.

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 long but every segment earns its place: the front-loaded analysis-surface list, the bracketed routing rule, the sibling disambiguation, and the UI-switch caveat. It is dense rather than padded, and the bracket-delimited routing rule keeps the decision-critical information scannable despite overall length.

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?

This is a complex 8-parameter tool with no output schema, and the description covers the breadth of what it produces well. However, it does not describe the shape of returned data (e.g., what brief=true truncates or how results are keyed by chapter), and it omits prerequisites such as which books are analyzable even though novel_books exists as a sibling. Good enough for tool selection, slightly thin for confident invocation.

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's category enumeration (high-frequency templates, emotion curve, chapter-level rhythm sequences) maps loosely onto top, curveSegments, and chapter, adding mild output context that helps parameter understanding. However, it adds no syntax, format, range, or default information beyond the schema, so it does not exceed the baseline.

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 specifies a concrete analytical verb (统计/分析) bound to a clear resource (某部作品或单章) and enumerates the full analysis surface: nine sentence-type categories, arrangement patterns, paragraph structure, sentence-length distribution, emotion curve, style fingerprint, and rhythm suggestions. It also explicitly distinguishes itself from novel_style_check and novel_style_report by question type, so an agent can identify it without opening schemas.

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 bracketed rule 【问「这本书是怎么写的」时用它】 gives the exact condition for calling this tool, and it names two sibling alternatives with their own trigger questions (novel_style_check=「我这一章写得像不像」, novel_style_report=「这本书是什么风格」), explicitly asserting they are different questions rather than duplicates. It also flags the UI-switch prerequisite and routes the agent to novel_sentence_config for status checks — full alternative and precondition guidance.

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