DiffiCat

Start comparison

start_comparison

Compare Site A against Site B on page existence, content and visual regression. Charged upfront in USDC (the 402 challenge names the network): 0.02 USD per page for the first 1000 pages and 0.01 USD per page beyond. maxPages is optional: a ceiling, not a reservation. A job is priced on the pages it compares (the urls list, or the pages discovery finds, at most maxPages), the challenge names the count, and there is no page limit. Poll get_comparison, then get_report (paged with offset and limit).

Input Schema

TableJSON Schema

Name	Required	Description
`urls`	No	Explicit page pairs to compare; skips discovery and is priced per pair.
`maxPages`	No	Optional ceiling on the pages compared and charged for. The job is priced on the pages it compares: the urls list, or the pages discovery finds, at most this many. There is no page limit.
`sourceUrl`	Yes	Site A, the reference site (full URL).
`targetUrl`	No	Site B, the migrated site. Omit to capture screenshots of Site A only.
`threshold`	No	Visual diff tolerance as a fraction, 0 (exact) to 1.
`sitemapUrl`	No	Sitemap to discover pages from.
`sourceAuth`	No	HTTP basic auth for Site A.
`targetAuth`	No	HTTP basic auth for Site B.
`viewportWidth`	No	Capture width in px.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 26, 2026

changedInput schema / properties / maxPages / description

Previous value: -"Optional page cap, 1-500: pay for this many and compare at most this many. Without it (and without urls) the job is priced on the pages discovery finds, capped at 500."New value: +"Optional ceiling on the pages compared and charged for. The job is priced on the pages it compares: the urls list, or the pages discovery finds, at most this many. There is no page limit."

changedInput schema / properties / maxPages / maximum
```
Previous value: -500New value: +9007199254740991
```
removedInput schema / properties / urls / maxItems
```
Removed value: -500
```

Changed4 schema fields changedSep 26, 2026

changedInput schema / properties / maxPages / description

Previous value: -"Pages to reserve and pay for, 1-500. The job compares at most this many."New value: +"Optional page cap, 1-500: pay for this many and compare at most this many. Without it (and without urls) the job is priced on the pages discovery finds, capped at 500."

changedInput schema / properties / urls / description

Previous value: -"Explicit page pairs to compare; skips discovery when given."New value: +"Explicit page pairs to compare; skips discovery and is priced per pair."

addedInput schema / properties / urls / minItems
```
Added value: +1
```

changedInput schema / required

Previous value: -[
-  "sourceUrl",
-  "maxPages"
-]New value: +[
+  "sourceUrl"
+]

First observedSep 25, 2026

TDQS

A4.4/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses the upfront USDC charge, per-page pricing tiers, the fact that maxPages is a ceiling not a reservation, and the absence of a page limit. It also notes that omitting targetUrl captures screenshots of Site A only, adding behavioral nuance.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, front-loaded with the primary purpose, then pricing, then maxPages nuance, then workflow. Every sentence contributes new information with zero redundancy.

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 tool with 9 parameters, nested objects, and no output schema, the description covers the key aspects: purpose, pricing, parameter interplay, and follow-up workflow. It does not mention error cases or explicit auth requirements, but those are implicit in the schema. Overall, it gives an agent enough to invoke the tool correctly.

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 coverage is 100% and each parameter already has a useful description. The description adds value by clarifying the interaction between urls and maxPages (pricing on compared pages, maxPages as a ceiling) and the overall pricing semantics, going beyond the individual parameter descriptions.

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 clearly states a specific verb-resource pair: 'Compare Site A against Site B on page existence, content and visual regression.' This distinguishes it from siblings like capture_screenshot and discover_pages by naming the comparison objective and the two sites involved.

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 description gives workflow guidance ('Poll get_comparison, then get_report') and explains the pricing model, but it does not explicitly contrast with alternatives or state when not to use it. The purpose is obvious, so context is clear, but exclusions or explicit sibling routing are absent.

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

All DiffiCat tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?