LMX Cloud LLM Inference

extract_pdf

Extract text and light structure (title, headings, page count) from a PDF via LMX pdf-extract. Provide file_url and/or file_base64. Requires a real LMX API key (same gate as web_search).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "extract_pdf"
  }
}

Input Schema

Name	Required	Description
`api_key`	No	Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call.
`file_url`	No	Optional https URL to fetch the PDF from. Provide this and/or file_base64.
`file_base64`	No	Optional base64-encoded PDF bytes (raw base64 or data:application/pdf;base64,...). Provide this and/or file_url.

Schema Changelog

Changes observed during successful MCP inspections.

AddedAug 11, 2026

TDQS

A4.2/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It discloses the auth prerequisite and the input options, and implies a read-only extraction operation. However, it omits behavioral details like input precedence when both file_url and file_base64 are provided, size limitations, or error behavior if neither input is given. It adds some context but not a comprehensive behavioral profile.

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?

Three sentences, each serving a purpose: purpose, input specification, and auth note. No filler words or redundant phrasing. Info is front-loaded with the primary description first.

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 no output schema, the description adequately conveys what the tool returns ('text and light structure (title, headings, page count)') and how to invoke it. It could mention potential limitations (e.g., max PDF size) or the behavior when no input is supplied, but given the simple nature and optional parameters, it is reasonably complete.

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?

All three parameters have schema descriptions, giving 100% coverage. The description adds the 'and/or' requirement for file_url and file_base64, which is not enforced by the schema, and clarifies the api_key's role ('Optional... Prefer MCP client Authorization header or env'). This adds meaning beyond the schema, though not extensively.

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 the specific verb 'Extract' and resource 'PDF', and enumerates the output aspects ('text and light structure (title, headings, page count)'). It distinguishes itself from all siblings (e.g., web_search, chat_completion), none of which offer PDF extraction. The purpose is unambiguous and specific.

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 provides clear input requirements ('Provide file_url and/or file_base64') and a prerequisite ('Requires a real LMX API key (same gate as web_search)'). It doesn't explicitly name alternatives, but there are no sibling tools for PDF extraction, so the tool's purpose implies when to use it. The guidance is clear context though not an exhaustive when/when-not list.

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

All LMX Cloud LLM Inference 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?