site-audit

summarize

Read-onlyIdempotent

PAID CAPABILITY ($0.033 USDC per successful summary via x402 v2). Summarizes one public HTML page into a Claude-generated structured summary (title, summary, key_facts, entities, word_count) with an optional focus steering prompt; non-HTML targets return 422 and never settle. This MCP call validates the target and returns the canonical x402 HTTP handoff; payment and the result are exchanged at POST https://api.santosautomation.com/v1/summarize with {"url": "…"} (or GET ?url=&focus=). No account or API key is required.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	A publicly reachable HTTP or HTTPS page.
`focus`	No	Optional steering prompt for the summary, e.g. "pricing plans".

Output Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	Exact URL to request, then pay for and retry.
`method`	Yes	HTTP method to use for the paid request.
`network`	Yes	CAIP-2 chain id, eip155:8453 (Base mainnet).
`settles`	No	When funds move.
`protocol`	Yes	x402-v2
`price_usdc`	Yes	Price in USDC for one successful call.
`payment_required`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 31, 2026

removedOutput schema / properties / free_preview_url

Removed value: -{
-  "description": "Free alternative, where one exists.",
-  "format": "uri",
-  "type": "string"
-}

Changed1 schema field changedJul 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "free_preview_url": {
+      "description": "Free alternative, where one exists.",
+      "format": "uri",
+      "type": "string"
+    },
+    "method": {
+      "description": "HTTP method to use for the paid request.",
+      "type": "string"
+    },
+    "network": {
+      "description": "CAIP-2 chain id, eip155:8453 (Base mainnet).",
+      "type": "string"
+    },
+    "payment_required": {
+      "const": true,
+      "type": "boolean"
+    },
+    "price_usdc": {
+      "description": "Price in USDC for one successful call.",
+      "type": "string"
+    },
+    "protocol": {
+      "description": "x402-v2",
+      "type": "string"
+    },
+    "settles": {
+      "description": "When funds move.",
+      "type": "string"
+    },
+    "url": {
+      "description": "Exact URL to request, then pay for and retry.",
+      "format": "uri",
+      "type": "string"
+    }
+  },
+  "required": [
+    "payment_required",
+    "protocol",
+    "method",
+    "url",
+    "price_usdc",
+    "network"
+  ],
+  "type": "object"
+}

AddedJul 26, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds substantial behavioral context beyond those: the payment requirement, the 422 error for non-HTML targets, the canonical x402 HTTP handoff, and the exact endpoint for payment and result exchange. It also notes that no API key is required. No contradictions with annotations.

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 dense but every sentence earns its place: cost, functionality, output fields, focus capability, error behavior, handoff details, endpoint, and requirement of no account. It is front-loaded with the most important usage determinant (paid capability) and structured logically from what it does to how to call it.

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

Completeness5/5

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

The tool has an output schema, so return values are documented. The description covers input requirements, error handling, payment flow, endpoint, and lack of authentication. Nothing an agent needs to correctly invoke the tool is missing; the information is complete and actionable.

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?

The schema already describes both parameters (url is a publicly reachable HTTP/HTTPS page, focus is an optional steering prompt), so coverage is 100%. The description adds value by explaining the output structure (title, summary, key_facts, entities, word_count) and clarifies that focus steers the summary, slightly enriching semantics beyond the schema. No enums or nested objects require extra explanation.

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 states a specific verb ('summarizes'), a specific resource ('one public HTML page'), and the exact output structure ('title, summary, key_facts, entities, word_count'). This clearly distinguishes it from sibling extraction tools like extract_page_markdown or extract_structured_data, which have different purposes.

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 clarifies when the tool applies ('public HTML page') and when it fails ('non-HTML targets return 422'), and it explicitly notes the cost ('PAID CAPABILITY') as a usage consideration. However, it does not explicitly enumerate alternatives or say 'use this when you need a summary, not raw extraction', leaving some comparison to inference from the sibling list.

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

All site-audit 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?