pdfintact

Convert PDF

convert_pdf

Convert a PDF into structured content (tables, charts, formulas, headings, body text) using a two-stage pipeline (layout detection, then a vision-language model) rather than a single VLM call on the raw PDF -- calling a VLM on a raw PDF directly is a known-unreliable pattern for numeric tables.

Measured accuracy (500-page real-world benchmark of government/corporate reports, ~51,000 table values checked): tables 95.2% digit-exact, body text 88.8%. This tool reads PDFs a VLM cannot read directly, including scanned pages and PDFs with corrupted/garbled text layers (common in older Japanese academic PDFs). For scanned Japanese documents the numbers hold up (99.4% on the same benchmark). For scanned Arabic, body text does NOT: characters are dropped mid-sentence and quantities can turn into different quantities, so body blocks from scanned Arabic are always flagged confidence:"estimated" -- tables in the same documents stayed exact in our measurement. Strong on Japanese-language documents specifically; the accuracy figures above were measured on Japanese material and are not a claim about every language. Chart values are extracted but are best-effort estimates (about 52% exact match, excluding axis tick labels) and are always flagged confidence:"estimated" in the result -- do not treat estimated chart numbers as authoritative.

This is a PAID, ASYNCHRONOUS, per-page-billed operation: credits are reserved from the caller's PDFIntact balance before processing starts, and the response's _meta.credits_remaining shows the balance right after reservation. Processing takes real wall-clock time (roughly 7 seconds/page; a 500-page PDF takes about 42 minutes including a multi-minute cold start), so this tool returns a job_handle immediately without waiting -- call get_result with that job_handle to poll for completion instead of calling convert_pdf again. Always pass idempotency_key; reuse the exact same value if you retry the same request, otherwise retries can double-charge and double-process. Provide the PDF either as a public https URL (source.type="url", up to ~200MB) or inline base64 (source.type="base64", up to ~20MB) -- prefer the URL form for large files.

Requires sign-in (OAuth): this session is not authenticated, so calling this tool will fail until the PDFIntact account is connected and authorized.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`source`	Yes
`idempotency_key`	Yes	Unique key for this request. Reuse the same value on retry of the same PDF to avoid double charging.

Schema Changelog

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

First observedSep 3, 2026

TDQS

A5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden, and it excels: it discloses that this is paid, asynchronous, per-page billed, reserves credits, takes real wall-clock time, returns a job_handle, and can double-charge on retries. It also provides measured accuracy caveats and confidence-flag behavior, which are essential for interpreting results.

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?

The description is long, but every section earns its place: core function, pipeline rationale, language-specific accuracy, billing/async behavior, input formats, idempotency, and auth requirements. It is front-loaded with the what and immediately follows with operational constraints, with no filler.

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

Completeness5/5

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

For a complex, paid, asynchronous operation with no output schema and no annotations, this description is remarkably complete. It covers invocation prerequisites, parameter semantics, known failure modes, timing, billing, and the follow-up get_result flow, so an agent can decide whether and how to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the source object and idempotency_key only minimally. The description adds substantial meaning: URL is for public https sources up to ~200MB, base64 for inline data up to ~20MB, prefer URL for large files, and idempotency_key must be reused on retries to prevent double processing. This goes well beyond the schema.

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 opens with a clear verb and resource: 'Convert a PDF into structured content' and lists the content types produced. It also distinguishes itself from siblings by explaining that it returns a job_handle and that polling should be done via get_result.

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

Usage Guidelines5/5

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

It gives explicit operational guidance: use get_result to poll instead of calling convert_pdf again, prefer URL for large files, reuse idempotency_key on retry to avoid double charging, and warns that the current unauthenticated session will fail. This fully addresses when and how to use the tool versus alternatives.

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

All pdfintact tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.9/5.0

Disambiguation5/5

Each tool has a clearly distinct role: convert_pdf starts an async conversion job, get_result polls that job, and get_balance checks account credits. There is no meaningful overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow the same snake_case verb_noun pattern: convert_pdf, get_balance, get_result. The naming is predictable and immediately signals each tool's action and target.

Tool Count5/5

Three tools is well-scoped for this server's purpose: submit a conversion, retrieve the result, and check the prerequisite credit balance. Each tool earns its place in the minimal async workflow.

Completeness5/5

The core lifecycle is fully covered: convert_pdf creates the job, get_result reads its status and output, and get_balance handles the payment/credit prerequisite. No essential operation for this narrow domain is missing, and there are no dead ends in the workflow.

Resources

Need Help?