Skip to main content
Glama

NS Pros MCP Gateway

nsf-awards__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": "nsf-awards__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

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses that the diff is over readable text rather than markup, and warns that a restyled-but-identical page will report changed:false — a genuine false-negative caveat an agent needs. It omits operational traits such as rate limits, failure behavior on missing captures, and permissions, which keeps it below a 5.

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?

It is front-loaded with the guiding question and then packs mechanism, output shape, and the key caveat into one dense sentence. However, that sentence is long and run-on, and the text is truncated mid-word ('with the reason (sa'), which leaves a dangling fragment that costs clarity.

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?

For a four-parameter tool with no output schema and no annotations, the description covers what matters: the resolution strategy, the returned fields (removed/added segments, similarity score, capture timestamps and gaps), and the changed:false semantics. The truncation leaves the changed:false reason payload and the no-capture-available case underspecified.

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 all four parameters are already documented, including max_gap_days with its default and cap. The description adds only contextual meaning ('the archived capture nearest each date', 'gaps from the requested dates') without new syntax or constraints, so the baseline 3 applies.

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?

The description names a concrete verb and resource ('resolves the archived capture nearest each date... extracts the readable text of both, and returns a text-level diff') and even enumerates the upstream sources (Wayback, Common Crawl, Arquivo.pt). It does not explicitly contrast itself with the sibling archive_evidence tool, which is the main thing separating a 4 from 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 Guidelines3/5

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

The opening question 'What changed on a web page between two dates?' implies the use case, and the changed:false discussion hints at when results should be trusted. There is no explicit when-not guidance, no mention of the single-capture sibling archive_evidence, and no statement about what happens when no capture exists near a date.

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.