修改章节

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

With no annotations, the description carries the full behavioral burden and does disclose two non-obvious traits: the editor auto-saves as it types, and the default mode performs no filling at all (read + screenshot only). It does not describe permission/auth requirements, failure modes, or what the call returns, and the screenshot/preview output format is only alluded to.

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-loaded with the action and scoping, then the critical confirm rule; the parenthetical asides are short and each carries information. Slightly dense with two levels of parenthetical nesting, but no filler sentences.

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, no-output-schema tool, the description covers the highest-risk aspects (auto-save, default read-only preview, body source options, chapter_id origin). It leaves headless, scheduled_time, chapter_number and the shape of the read-mode result to the schema, which documents them, so the gap is minor.

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 description coverage is 100%, so every parameter including confirm, book_id, chapter_id and the content/file_path/article_id trio is already documented in the schema. The description restates the three-way body-source choice and the confirm gate but adds no format, precedence, or syntax detail beyond the schema (article_id 优先 is already in the schema). Baseline 3 applies.

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 (修改已有章节的标题/正文) and the mechanism used (走章节编辑器，按 chapter_id 定位), which separates it from add_chapter_qimao and delete_chapter_qimao at a glance. An agent can identify this as the edit-existing-chapter tool without opening 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?

Gives a concrete operating rule: confirm=false only opens the page, reads current state and takes a screenshot; confirm=true actually fills and submits. That is real when-to-use guidance for a risky mutation. It stops short of naming alternatives (e.g. update_novel for body text, add_chapter_qimao for new chapters) or prerequisites like required login.

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