新增小说（建书）

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

With no annotations the description carries the full burden, and it delivers the most important trait: the write is gated behind confirm=true, defaulting to a safe dry-run preview. It also enumerates tag caps, which is real behavioral detail. It omits auth/prerequisite state, failure modes, and rate limits.

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?

Dense and front-loaded: purpose first, then required fields, then tag caps, then the confirm gating. Every clause carries an actionable constraint (lengths, caps, mode) with no filler.

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 10-parameter mutation tool with no annotations and no output schema, the description covers the core requirements and the critical confirm gate well. It leaves headless, register_local, and reading_tags unexplained and says nothing about the return shape or post-submission 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?

Schema coverage is 100%, so baseline is 3, but the description adds genuine value beyond it by giving the numeric tag ceilings (情节≤4/情感≤2/人设≤4/世界观≤1) that the schema only gestures at as '各有上限'. It restates the required fields and length limits rather than adding new meaning for title/gender/abstract.

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+resource with scope: '在番茄作者后台真实建书' (actually create a book on the Tomato author backend). The '真实' qualifier and '建书' distinguish it from siblings like create_short_story_tomato and add_chapter_tomato without needing the schema.

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 defines the two operating modes: '默认 confirm=false 只做预检与预览，不建书；confirm=true 才真正提交' — a clear when-to-use-each-condition rule. It stops short of naming sibling alternatives or prerequisites (e.g. login_tomato must run first), so 4 rather than 5.

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