Skip to main content
Glama
scrape-mcp
by guanyuyan

web_history

Lists saved snapshot versions for a target URL without fetching the page, enabling version selection for retrieval or change comparison and time-based lookup.

Instructions

列出一个 URL 的历史快照版本(由 web_watch 建立),不抓取页面。

版本号从 1(最新)递增,可直接作为 web_fetch(version=...) / web_changes(compare=...) 的入参;captured_at 为 UTC 时间,也可用 ISO 时间点定位"某时刻之前最近的版本"。 快照默认最多保留 20 版 / 90 天(SCRAPE_MCP_WATCH_MAX_VERSIONS / WATCH_RETENTION_DAYS)。

Args: url: 目标网页完整 URL。 selector: 与 web_watch 时一致的选择器;不传表示整页快照。 limit: 最多返回的版本数,1~100,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_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
limitNo
selectorNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.35.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it discloses version numbering (1 = newest, ascending), that captured_at is UTC and supports ISO-time lookup of the nearest prior version, plus retention limits (20 versions / 90 days) and the env vars controlling them. It does not explicitly state permission or auth requirements, so it is not exhaustive.

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?

The purpose and non-behavior are front-loaded in the first line, followed by version semantics and then a compact Args block. The retention sentence is relevant but slightly tangential relative to the core listing behavior; otherwise there is no padding.

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

Completeness5/5

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

For a 3-parameter read tool with an output schema already covering return values, the description supplies everything needed: what it lists, version numbering, time-based addressing, parameter meaning and limits, and the retention/setup dependency on web_watch. Nothing an agent needs in order to call it correctly is missing.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate and largely does: url is defined as the full target URL, selector is tied to the selector used at web_watch time with "absent = whole page", and limit gets the undocumented range 1~100 and default 20. Only the url definition adds little beyond the parameter name.

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 starts with a specific verb and resource ("列出一个 URL 的历史快照版本") and immediately draws a boundary by noting the snapshots are created by web_watch and that no page is fetched. An agent can distinguish this from web_fetch/web_watch without opening any 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 clearly states the context of use (inspecting stored versions) and explains how the output feeds into web_fetch(version=...) and web_changes(compare=...). It also implies "not for fetching pages" as an exclusion, but never names an explicit alternative tool to use instead for fetching, so it stops just short of full when/when-not guidance.

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