Skip to main content
Glama

NS Pros MCP Gateway

ntsb-investigations__archive_compare

What changed on a web page between two dates? Resolves the archived capture nearest each date (Internet Archive Wayback Machine, Common Crawl, Arquivo.pt), extracts the readable text of both, and returns a text-level diff: the segments removed and added, a similarity score, and both capture timestamps with their gaps from the requested dates. It diffs readable text, not markup, so a restyled page with the same words reads changed:false. Identical captures answer changed:false with the reason (sa

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "https://www.ftc.gov/policy-notices/privacy-policy",
      "date_a": "2022-06-02",
      "date_b": "2024-06-15"
    },
    "name": "ntsb-investigations__archive_compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe page address, e.g. "https://www.ftc.gov/policy-notices/privacy-policy".
date_aYesThe earlier date, as YYYY-MM-DD (e.g. "2021-06-01").
date_bYesThe later date, as YYYY-MM-DD (e.g. "2024-06-01").
max_gap_daysNoFurthest a capture may be from each date and still be used, in days. Default 30, max 3650.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
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 well on disclosure of sources, return contents (removed/added segments, similarity score, both timestamps and their gaps), the text-only limitation, and the changed:false semantics with an explanatory reason. It is silent on what happens when no capture exists within the max_gap_days window, and the final sentence is truncated ('with the reason (sa'), leaving the stated behavior incomplete.

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 front-loaded question immediately frames the task, and the remaining sentences each add substantive detail about sources, return shape, and the text-vs-markup limitation. The one flaw is the trailing truncated fragment, which leaves an unfinished thought.

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

Completeness3/5

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

With no output schema and no annotations, the description must cover both return values and behavior, and it largely does by naming the diff segments, similarity score, and capture timestamps. It is incomplete on failure modes (no capture found within the gap, source outages) and ends mid-sentence, so an agent still lacks the full picture of what a negative result looks like.

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

Parameters3/5

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

Schema description coverage is 100%, so every parameter is already documented, giving a baseline of 3. The description adds some meaning by explaining that each date is matched to the nearest archived capture and that returned timestamps include gaps from the requested dates, which clarifies the semantics of date_a/date_b and max_gap_days beyond the schema. That lifts it slightly, but it adds no format or edge-case guidance for the gap parameter.

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

Purpose4/5

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

A specific verb and resource: it resolves archived captures near two dates and diffs their readable text. The mechanism (Wayback, Common Crawl, Arquivo.pt) and the nature of the diff are stated precisely, so an agent knows exactly what the tool produces. It does not contrast itself with siblings such as archive_evidence or recent_changes, which is why it falls short of a 5.

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?

The framing question and the 'between two dates' scope make the use case obvious, and the markup-vs-text caveat tells the agent when this tool will report changed:false even though the page looks different. There is no explicit when-not guidance or named alternative for retrieving a single capture rather than comparing two.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.