Skip to main content
Glama

Convert document to Markdown (MarkItDown)

api2pdf_convert_to_markdown
Destructive

Convert a document or file (given as a URL — PDF, Office docs, and more) to Markdown text via MarkItDown. Great for feeding a document's contents back to an agent. Returns a { FileUrl } (valid ~24h). BILLED. Api2Pdf API: POST /markitdown.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the document/file to convert to Markdown.
inlineNoIf true (Api2Pdf default), the generated file is served inline; if false, as an attachment.
optionsNoEngine-specific render options (page size, margins, orientation, headers/footers, etc.). Passed through verbatim to Api2Pdf.
storageNoCustom storage target, used when useCustomStorage is true.
fileNameNoA name for the generated file, e.g. 'invoice.pdf'.
output_binaryNoIf true, return the raw file bytes as base64 instead of a FileUrl. Default false (recommended for agents — returns a short-lived link).
extraHTTPHeadersNoExtra HTTP headers Api2Pdf forwards when it fetches a source URL (e.g. auth for a protected page/file).
useCustomStorageNoIf true, Api2Pdf uploads the result to your own storage (see `storage`) instead of hosting it.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

The annotations already carry destructiveHint=true; the description adds valuable behavioral context beyond that by disclosing that the operation is BILLED, that the returned FileUrl is valid only ~24h, and by giving the exact API endpoint. It does not elaborate on what destructive behavior might occur, which prevents a 5.

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 short sentences with no filler. The main action is front-loaded, followed by the use case, return behavior, billing flag, and API endpoint—each sentence earns its place.

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 an 8-parameter tool with nested objects and no output schema, the description covers the essential invocation facts: input URL, output as FileUrl with 24h expiry, billing, and API endpoint. It leaves minor gaps around alternatives and the exact response shape, but the schema covers parameter details.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds format guidance ('PDF, Office docs, and more') for the url parameter that goes beyond the schema's generic 'document/file' wording, giving agents useful selection context.

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 conversion direction ('Convert a document or file ... to Markdown text'), names the engine (MarkItDown), and scopes the input as a URL covering PDF and Office docs. This makes it easy to distinguish from sibling conversion tools like api2pdf_markdown_to_pdf or api2pdf_office_to_pdf.

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?

It gives a clear use case ('Great for feeding a document's contents back to an agent') and notes the URL-based input. It does not explicitly name alternatives or state when not to use the tool, so it falls short of a 5.

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.

TDQS

A4.3/5.0
Disambiguation5/5

Each tool targets a distinct operation: conversions, PDF manipulations, file deletion, and account/service info are clearly separated. Even the three HTML-to-PDF tools are distinguished by source type or rendering engine.

Naming Consistency5/5

All tools follow a consistent api2pdf_ prefix with snake_case verb-based names such as add_password, merge_pdfs, and url_to_pdf. The pattern is predictable and makes it easy to infer what each tool does.

Tool Count4/5

Sixteen tools is slightly above the typical 3-15 range, but the count is justified by the breadth of Api2Pdf's functionality spanning creation, manipulation, conversion, deletion, and account management.

Completeness5/5

The surface covers the full PDF lifecycle: generate from multiple sources, manipulate via merge/extract/compress/password, convert to markdown, delete files, plus billing and status checks. No obvious missing operations for the documented purpose.