Describe a scraping task in plain language to have AI generate the configuration, run the scraper, repair failures, and return structured results—no selectors needed.
用一句话描述爬虫任务，AI 自动生成配置、自动运行、失败自修复，返回结构化结果。适合：不会写选择器/配置的非技术用户。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 最多抓取条数（可选） | |
| rounds | No | 自动重试轮数（默认 2，失败会自修复配置） | |
| description | Yes | 中文/英文任务描述，如：抓取 https://quotes.toscrape.com/ 的名言、作者和标签，翻 2 页 |
Changes observed during successful MCP inspections.
v2.2.0Does 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 usefully discloses the multi-stage pipeline (config generation, execution, failure self-repair) and that output is structured, but says nothing about latency, cost, terminal-failure behavior when self-repair is exhausted, or whether any state is persisted.
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?
Two compact sentences: the capability pipeline is front-loaded, then the audience qualifier. Nothing is redundant and no sentence restates the schema.
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?
With three simple parameters and full schema coverage, the input side is well covered. However, there is no output schema, so the vague claim "返回结构化结果" leaves the shape of the returned data undefined for an agent that must decide whether the result is usable — a gap that should have been spelled out.
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 all three parameters (description, limit, rounds) are already documented in the schema, including the retry semantics of rounds and an example task string. The description adds no format or syntax guidance beyond what the schema already supplies, so the 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?
The description states a specific verb chain (auto-generate config → auto-run → self-repair) and resource (crawler task) plus a structured return, which is far more specific than the ambiguous name 'auto'. It implicitly distinguishes itself from config-driven siblings like scrape/crawl by targeting users who "不会写选择器/配置", but it never names those siblings explicitly.
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?
It gives an explicit target-user condition — "适合：不会写选择器/配置的非技术用户" — which tells the agent this is the zero-config entry point. It does not name alternatives (scrape, crawl, extract) or state when NOT to use this tool, so routing still requires the agent to infer from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.