Skip to main content
Glama

NS Pros MCP Gateway

ntsb-investigations__archive_evidence

What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a cap

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.sec.gov",
      "date": "2023-06-01"
    },
    "name": "ntsb-investigations__archive_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe page address, e.g. "https://www.sec.gov" or "https://www.ftc.gov/policy-notices/privacy-policy".
dateYesThe date to look up, as YYYY-MM-DD (e.g. "2023-06-01"), YYYYMMDD, or a full ISO timestamp.
max_charsNoCharacters of page text to return. Default 12000, max 60000.
max_gap_daysNoFurthest a capture may be from the date and still be used, in days. Default 30, max 3650.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose a lot: three source archives are queried, HTML is stripped to readable text, and the gap between requested and actual capture date is reported with an example format. It does not cover failure behavior when no capture exists (the sentence is truncated mid-word), nor any rate-limit, retry, or fallback ordering across the three archives.

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 the core question, then a single dense sentence covering sources, processing, and return payload, with the chaining substitution placed last. Every sentence carries information; the only weakness is that the closing conditional is truncated, leaving an incomplete thought dangling at the end.

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?

There is no output schema, so the description must describe return values and it does: readable text with HTML stripped, capture timestamp, archive link, and a quantified date gap. Combined with a fully-documented 4-parameter schema, an agent has enough to call it correctly, with the only real hole being the unexplained no-capture case left incomplete by the truncation.

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 coverage is 100%, so all four parameters including max_gap_days and max_chars are already documented in structured form, establishing a baseline of 3. The description adds genuine meaning only for 'date' — clarifying that it selects the nearest capture and that the resulting gap is surfaced to the caller — but adds nothing further about max_chars or how the three sources are prioritized.

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?

Opens with a concrete question ('What did a web page say on a given date?') and then states a specific verb and resource: find the nearest archived capture of a URL across three named archives and return its readable text. The multi-archive 'nearest capture' framing implicitly distinguishes it from a diffing sibling like archive_compare, but it never names that sibling, so the differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The line 'One call replaces the find-capture, fetch-record, parse-HTML chain' gives real usage context — reach for this instead of manually chaining retrieval and parsing steps. However, there are no explicit exclusions, no named alternative (e.g. archive_compare for comparing two points in time), and the trailing sentence about what happens when no archive holds a capture is cut off, so the guidance stops at implied.

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.