Skip to main content
Glama

chgwatch__diff

Durable-baseline diff of one or two URLs: returns changed, hashes, added/removed sentence samples. Stores a baseline you can diff against later; add baseline=stored to compare to the last stored snapshot. Price: $0.01 per call in USDC on Base (eip155:8453), paid with x402 in params._meta["x402/payment"]. HTTP: GET https://api.firstmention.uk/s/chgwatch/diff

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": "chgwatch__diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
modeNotext (default), markdown, meta or links
url2NoOptional second URL to compare against instead of a stored baseline

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • removedInput schema / properties / baseline
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / mode / description
      Added value: +"text (default), markdown, meta or links"
    • addedInput schema / properties / url2
      Added value: +{
      +  "description": "Optional second URL to compare against instead of a stored baseline",
      +  "type": "string"
      +}
    • addedInput schema / required
      Added value: +[
      +  "url"
      +]
  2. Changed1 schema field changed
    • removedInput schema / required
      Removed value: -[
      -  "url"
      -]
  3. Changed5 schema fields changed
    • addedInput schema / properties / baseline
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / mode / description
      Removed value: -"What to compare"
    • removedInput schema / properties / mode / enum
      Removed value: -[
      -  "text",
      -  "markdown",
      -  "meta",
      -  "links"
      -]
    • removedInput schema / properties / store
      Removed value: -{
      -  "description": "true to save this snapshot as the new baseline",
      -  "type": "string"
      -}
    • removedInput schema / properties / url / description
      Removed value: -"URL to diff against its stored baseline"
  4. Changed7 schema fields changed
    • removedInput schema / description
      Removed value: -"Use watchlist=1 to poll your saved list, or urls=a,b,c for a batch check. Your watchlist is stored server-side under your payer wallet, so you never resend URLs."
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "What to compare",
      +  "enum": [
      +    "text",
      +    "markdown",
      +    "meta",
      +    "links"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / store
      Added value: +{
      +  "description": "true to save this snapshot as the new baseline",
      +  "type": "string"
      +}
    • addedInput schema / properties / url
      Added value: +{
      +  "description": "URL to diff against its stored baseline",
      +  "type": "string"
      +}
    • removedInput schema / properties / urls
      Removed value: -{
      -  "description": "Comma-separated URLs to batch-check (up to 20). Omit when watchlist=1.",
      -  "type": "string"
      -}
    • removedInput schema / properties / watchlist
      Removed value: -{
      -  "description": "Set to 1 to check every URL in your saved watchlist (keyed to your paying wallet).",
      -  "type": "string"
      -}
    • addedInput schema / required
      Added value: +[
      +  "url"
      +]
  5. Changed3 schema fields changed
    • addedInput schema / description
      Added value: +"Use watchlist=1 to poll your saved list, or urls=a,b,c for a batch check. Your watchlist is stored server-side under your payer wallet, so you never resend URLs."
    • addedInput schema / properties / urls
      Added value: +{
      +  "description": "Comma-separated URLs to batch-check (up to 20). Omit when watchlist=1.",
      +  "type": "string"
      +}
    • addedInput schema / properties / watchlist / description
      Added value: +"Set to 1 to check every URL in your saved watchlist (keyed to your paying wallet)."
  6. Changed8 schema fields changed
    • removedInput schema / properties / baseline
      Removed value: -{
      -  "enum": [
      -    "stored",
      -    "watch"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / context_lines
      Removed value: -{
      -  "maximum": 500,
      -  "minimum": 0,
      -  "type": "integer"
      -}
    • removedInput schema / properties / mode
      Removed value: -{
      -  "enum": [
      -    "text",
      -    "markdown",
      -    "meta",
      -    "links"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / prev_hash
      Removed value: -{
      -  "type": "string"
      -}
    • removedInput schema / properties / url
      Removed value: -{
      -  "description": "Single URL alternative to urls",
      -  "type": "string"
      -}
    • removedInput schema / properties / urls
      Removed value: -{
      -  "description": "Comma-separated URLs to check (max 20)",
      -  "type": "string"
      -}
    • addedInput schema / properties / watchlist
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "urls"
      -]
  7. First observed

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does disclose meaningful behavior: the tool persists a baseline snapshot (a side effect on server state), the transport (HTTP GET), the exact endpoint, and the payment requirement ($0.01 USDC on Base via x402 in params._meta). It does not cover retention/overwrite semantics for the stored baseline or rate limits, so it isn't 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 text is front-loaded with what the tool returns, then persistence, then pricing and transport, so an agent can stop reading early. The pricing/x402 clause and HTTP line are dense but each carries call-critical information; there is little pure filler.

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?

For a 3-parameter, no-annotation, no-output-schema tool, the description covers output shape and payment mechanics well. The unresolved 'baseline' parameter reference is a real completeness gap, since an agent trying to use the stored-snapshot mode has no schema-valid way to do it from this definition.

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 67% (url and url2 documented in-schema), so the baseline is 3. The description does add value by explaining the one-vs-two-URL pattern, but it also introduces 'baseline=stored', a parameter that does not exist in the schema, creating ambiguity about how the stored-comparison mode should actually be invoked.

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 specific verb+resource ("Durable-baseline diff of one or two URLs") and even sketches the return payload (changed flag, hashes, added/removed sentence samples). It doesn't name a sibling like chgwatch__diffmulti or chgwatch__since, so the boundary between this tool and the multi-URL/historical variants is left implicit.

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?

There is partial how-to guidance (use url2 to compare two live URLs, or add baseline=stored to compare against the last snapshot), which implies when this tool fits. However, no when-not guidance or explicit routing to sibling tools is given, and the referenced 'baseline' parameter does not appear in the input schema, so the agent is being steered toward a call shape that may not be valid.

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.

Resources