ETL-D MCP Server

extract_custom_v1_documents_custom_post

Extract structured data from PDFs by defining a custom JSON schema. Provide the PDF via URL or base64, then receive deterministic extraction enforced to your schema.

Instructions

Process a PDF with a user-defined JSON Schema.

Cost: 10 credits.

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": {
      "dynamic_schema": "<dynamic_schema>"
    },
    "name": "extract_custom_v1_documents_custom_post"
  }
}

Input Schema

Name	Required	Description
`pdf_url`	No	URL to the PDF file
`pdf_base64`	No	Base64 encoded PDF string
`dynamic_schema`	Yes	JSON Schema (JSON Object) to enforce on the extraction

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.2.0Aug 25, 2026

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only mentions a cost of 10 credits and the core action, but says nothing about side effects, read-only nature, output format, or any other behavioral context. It provides minimal value beyond the action itself.

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 description is extremely concise with two short sentences, containing no fluff. It front-loads the action and the key differentiator (custom schema), making it efficient to read. It's slightly under-specified, but for what it says, it's well-structured.

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

Completeness2/5

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

Given there is no output schema and no annotations, the description is incomplete for an agent to fully understand what the tool returns or what 'processing' entails. It doesn't clarify that the output is extracted data, nor does it explain how the schema influences the result. The agent is left with significant ambiguity about the tool's behavior beyond the immediate call.

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?

Since schema description coverage is 100%, all parameters are already described in the schema. The description adds no parameter-specific meaning beyond what's in the schema, so it meets the baseline for high coverage without providing extra semantic value.

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 states a specific action (process a PDF) and a defining characteristic (user-defined JSON Schema), which distinguishes it from specialized extractors like extract_invoice or extract_resume. However, 'process' is somewhat vague and doesn't explicitly say 'extract structured data', though the context and name imply it.

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?

There is no guidance on when to use this tool versus the many alternative extractors or enrichment tools. It doesn't mention when not to use it, nor does it suggest alternatives. The agent is left to infer its applicability from the name and schema alone.

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

Deploy Server