Skip to main content
Glama
Sign In

MorseByte x402 Edge Data Refinery & Quant Gateway

by io.github.Ceejaythenerd
OverviewDiscussionsAdmin

Workers AI Structured JSON Extractor

morsebyte_extract_json
Read-onlyIdempotent

Scrape a URL and extract structured JSON matching a prompt via Llama 3.3 70B ($0.030 USDC via x402).

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>",
      "prompt": "<prompt>"
    },
    "name": "morsebyte_extract_json"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesTarget webpage URL
promptYesExtraction instructions
schemaNoOptional JSON schema

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / prompt / description
      Previous value: -"Fields or instructions to extract as JSON"New value: +"Extraction instructions"
    • addedInput schema / properties / schema
      Added value: +{
+  "description": "Optional JSON schema",
+  "type": "object"
+}
  2. Changed7 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedInput schema / properties / prompt / description
      Previous value: -"Detailed description of the fields, entities, or tables to extract into structured JSON"New value: +"Fields or instructions to extract as JSON"
    • removedInput schema / properties / prompt / title
      Removed value: -"Extraction Instructions"
    • changedInput schema / properties / url / description
      Previous value: -"Public HTTPS URL to scrape prior to AI JSON extraction"New value: +"Target webpage URL"
    • removedInput schema / properties / url / format
      Removed value: -"uri"
    • removedInput schema / properties / url / title
      Removed value: -"Target Webpage URL"
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "extracted_json": {
-      "description": "Structured JSON object extracted by Llama 3.3 70B matching the user prompt",
-      "type": "object"
-    },
-    "latency_ms": {
-      "description": "Total scraping and AI inference latency in milliseconds",
-      "type": "number"
-    },
-    "provider": {
-      "description": "Service provider name",
-      "type": "string"
-    },
-    "source_url": {
-      "description": "Scraped source URL",
-      "type": "string"
-    }
-  },
-  "required": [
-    "provider",
-    "source_url",
-    "latency_ms",
-    "extracted_json"
-  ],
-  "type": "object"
-}New value: +null
  3. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so safety is covered. The description adds a genuinely useful behavioral fact the annotations do not carry: the cost ($0.030 USDC via x402). It says nothing about latency, page-size limits, truncation, or failure behavior when extraction cannot match the prompt, so it is only partly additive.

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?

One sentence, zero filler, core action front-loaded. The model name and price are appended where they are immediately useful rather than buried.

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?

With no output schema, the description should carry more of the return-shape and failure burden; 'structured JSON matching a prompt' is only a rough signal of what comes back. It also omits any mention of cost being incurred per call in context of retries and of what happens when the page is unscrapable. Adequate but with clear gaps for a paid, open-world extraction tool.

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 url, prompt and the optional schema object are already documented in the input schema. The description restates the prompt-extraction idea but adds no syntax, format guidance, or clarification of how the optional 'schema' parameter interacts with 'prompt'. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb+resource pair (scrape a URL, extract structured JSON) and names the mechanism (Llama 3.3 70B), which separates it from siblings like morsebyte_content_digest and morsebyte_llm_router. It does not, however, explicitly contrast itself against those siblings, so an agent still has to infer which tool fits which case.

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

Usage Guidelines2/5

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

The description gives no when-to-use condition, no exclusion criteria, and no pointer to an alternative tool. Usage is only implied by the phrase 'matching a prompt', leaving the agent to guess when this beats morsebyte_llm_router or morsebyte_content_digest.

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

All MorseByte x402 Edge Data Refinery & Quant Gateway toolsInspect
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