Skip to main content
Glama

ocr_text_paddle

Extract text from images using PaddleOCR, returning full text, per-line confidence scores, and bounding boxes for locating each line. Supports language selection via optional lang parameter.

Instructions

Extract text from an image. Returns full text, per-line confidence, and bounding boxes.

Backend: paddle. PaddleOCR CPU — cross-platform, mature model. Wider language support than Vision, but slower. Requires PaddleOCR Python package.

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": {
      "path": "<path>"
    },
    "name": "ocr_text_paddle"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo
pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • removedInput schema / properties / mode
      Removed value: -{
      -  "default": "base",
      -  "title": "Mode",
      -  "type": "string"
      -}
  2. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose the response shape, the runtime dependency ('Requires PaddleOCR Python package'), and a performance tradeoff. It omits anything about accepted image formats, local vs remote path behavior, or limits, which matters for a tool that reads from a filesystem path.

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?

Two tight sentences with the primary function front-loaded and backend details after; every clause carries information. Minor waste in the mild redundancy of 'Backend: paddle' plus 'PaddleOCR CPU' in the same sentence.

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?

For a two-parameter extraction tool with no output schema, the return-value and dependency coverage is adequate, but leaving both parameters undocumented is a meaningful gap given the reader must supply a path and optionally a language code. A competent agent can call it, but may mis-set `lang`.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate, and it does not. Neither 'path' (required) nor 'lang' is explained; the language discussion is framed as a backend capability rather than telling the agent that a `lang` argument exists or what values it accepts.

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?

Uses a specific verb and resource ('Extract text from an image') and adds the return payload (full text, per-line confidence, bounding boxes). It implicitly distinguishes itself from ocr_text_vision by contrasting 'wider language support' with 'slower', though it never names the alternative outright.

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?

Gives a real selection criterion: choose this over the Vision backend when language coverage matters more than speed, and notes the PaddleOCR Python package prerequisite. It stops short of explicit when-not-to-use guidance or naming sibling tools with overlapping intent (ocr_layout_paddle, ocr_table_paddle).

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