Skip to main content
Glama
scrape-mcp
by guanyuyan

web_changes

Compare two snapshots of a URL without new requests or extra scraping; get row-level diffs or field-level changes with deltas and percentages.

Instructions

比较某个 URL 的两个快照版本,不发请求、不产生额外抓取。

默认把最新版与上一版(compare="prev")比较;compare 也可填序号(1=最新)或 ISO 时间点(取该时刻之前最近的版本)。不传 schema 时退化为行级 diff; 传 schema 且两版快照都带字段数据时,输出字段级 changes(数值带 delta/pct)。 字段由 web_watch(schema=...) 随快照保存,历史快照没有字段数据时自动回退行级 diff。

Args: url: 目标网页完整 URL。 schema: 可选的字段抽取规则(同 web_extract),用于字段级比较。 compare: 与哪一版比较:prev(上一版,默认)/ 序号 / ISO 时间点。 selector: 与 web_watch 时一致的选择器;不传表示整页快照。 limit: 单类变更最多返回条数,1~50,默认 20。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "web_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
limitNo
schemaNo
compareNoprev
selectorNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.35.0

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose meaningful behavior: zero network requests, automatic degradation to row-level diff, and field-level output with delta/pct when both snapshots carry field data. It omits operational edge cases an agent would want, such as what happens when no prior snapshot exists, whether snapshots must have been created by web_watch, and any auth/scope requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then defaults, then fallback semantics, then a compact Args block. The Args section repeats a little of the prose (schema/compare) but each line carries distinct constraint information, so waste is minimal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and return-shape explanation is optional, yet the description still sketches the two output modes usefully. All five parameters are documented despite zero schema coverage. The only real gap is failure/empty-state behavior when there is no earlier snapshot to diff against.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates: every one of the five parameters is explained, including that compare accepts 'prev', a 1-based index (1=newest), or an ISO timestamp resolving to the nearest earlier version, that limit is bounded 1–50 with default 20, that selector must match the one used in web_watch, and that schema follows web_extract rules. This adds semantics the bare schema cannot express (the anyOf string|integer for compare is meaningless without this text).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: comparing two snapshot versions of a URL, and immediately adds the key differentiator '不发请求、不产生额外抓取', which separates it from the fetching siblings (web_fetch/web_extract/web_watch). An agent can tell what this does and what it does not do 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the default comparison target (prev), the acceptable alternative forms (index with 1=newest, or ISO timestamp meaning 'nearest version before that instant'), and the fallback path when no schema is given. It does not explicitly name a sibling as the alternative for the 'I need fresh data' case, but the no-request/no-crawl framing implies when this tool is the wrong choice.

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