Skip to main content
Glama

Tolca: business verification (KYB)

extract-url

extract_url
Read-onlyIdempotent

Fetch any public URL (HTML article, PDF, JSON) and return clean JSON matching YOUR schema in one call. No scraping code, no parsing: give a url and the fields you want. Input: url, schema (field -> type/description). Output: data + page title + source. Costs $0.03 USDC per call (x402 v2, Base or Solana). Send the HTTP header PAYMENT-SIGNATURE with your x402 payment, or call POST https://tolca.tonbot.ca/v1/extract-url with an x402 client.

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>",
      "schema": "<schema>"
    },
    "name": "extract_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic URL of an article, PDF or JSON document
schemaYesField name -> type or description
max_charsNoMax characters read from the document (1,000 to 60,000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / max_chars / description
      Added value: +"Max characters read from the document (1,000 to 60,000)"
    • addedInput schema / properties / url / description
      Added value: +"Public URL of an article, PDF or JSON document"
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations it discloses material behavior an agent cannot infer: a per-call price of $0.03 USDC on x402 v2 (Base or Solana), and the required PAYMENT-SIGNATURE header with a fallback POST endpoint for an x402 client. It also reveals the response shape ('data + page title + source'), so the agent knows what comes back without an output schema.

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 value proposition is front-loaded in the first sentence, then inputs, outputs and payment are presented in short labeled clauses with no filler. The payment sentence is dense but every element (price, network, header name, endpoint) is load-bearing, so little could be cut without losing needed information.

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?

With no output schema, the description correctly spells out the return payload, and the paid/x402 invocation path is fully explained, which is essential for correct use. The main residual gap is that max_chars (with its 1,000–60,000 range) is never referenced, and there is no note on failure modes such as unfetchable or non-public URLs.

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 the baseline is 3. The description restates the two required inputs and adds a compact gloss on the nested 'schema' object ('field -> type/description'), but it does not mention max_chars at all and adds no format or constraint detail beyond what the schema already documents.

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 names a specific verb and resource ('Fetch any public URL') and enumerates supported content types (HTML article, PDF, JSON). It also states the exact output contract ('clean JSON matching YOUR schema'), which separates it cleanly from a plain scraper or a text-only extractor among the siblings.

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?

It gives operational guidance about how to call it ('give a url and the fields you want', 'no scraping code, no parsing') and implicitly contrasts against building a scraper yourself. However, it never states when to prefer or avoid it relative to siblings such as extract or web_search, nor does it state any exclusion criteria (private URLs, paywalled pages, unsupported content types).

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.