Skip to main content
Glama

DeepSeek OCR

deepseek_ocr

Extracts text from local PDF, Word, PowerPoint, or image files via DeepSeek's OCR API and returns per-page text for downstream processing.

Instructions

Extract text from a local PDF, Word, PowerPoint or image file with DeepSeek's OCR API. Returns per-page text.

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": {
      "file_path": "<file_path>"
    },
    "name": "deepseek_ocr"
  }
}

Input Schema

NameRequiredDescriptionDefault
purposeNotext_recognition extracts text directly from text-only Office files and OCRs other files page by page; rich_layout_recognition OCRs every page.text_recognition
file_pathYesLocal path to a PDF, Word (doc/docx), PowerPoint (ppt/pptx), or image (png/jpeg/webp/gif/bmp/tiff). Max 100 MiB, 1000 pages.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It adds useful context by specifying local source files, supported formats, and per-page return structure, but omits error behavior, authentication requirements, and whether the operation is strictly read-only.

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?

Two concise sentences. The core action and resource are front-loaded, and the return format is stated without unnecessary detail.

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

Completeness3/5

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

The tool is relatively simple with two parameters and full schema coverage. The description covers scope and return shape, but without annotations or an output schema it could do more to explain failure modes, timeouts, or permission expectations.

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%, and the schema already explains file_path formats and limits plus the purpose enum. The description adds no parameter-level meaning beyond what the schema provides, so baseline 3 is appropriate.

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?

States a specific verb and resource: extract text from local PDF, Word, PowerPoint, or image files using DeepSeek OCR, and notes per-page output. This clearly distinguishes it from the media siblings such as ASR and TTS.

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?

The description does not state when to use this tool versus alternatives, nor does it mention prerequisites such as file accessibility or DeepSeek API availability. Usage is implied by the purpose but not guided.

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