Skip to main content
Glama

ocr_table_vision

Extract tables from images and convert them into structured CSV or JSON using on-device Apple Vision OCR, including CJK and European languages.

Instructions

Extract tables from an image. Returns structured CSV/JSON.

Backend: vision. Apple Vision OCR — fast on-device GPU/ANE inference (macOS 10.15+). Best for CJK + major European languages. Zero install on macOS.

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_table_vision"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo
modeNoaccurate
pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • changedInput schema / properties / mode / default
      Previous value: -"base"New value: +"accurate"
  2. First observedv1.0.0

TDQS

B3.2/5.0
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 does disclose useful traits such as the on-device GPU/ANE inference, the macOS 10.15+ platform requirement, and the CSV/JSON output shape. It says nothing about accuracy behavior, failure modes on unsupported platforms, or whether the 'mode' setting changes quality versus speed.

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 short sentences, front-loaded with the core action and return format, then a compact backend note. Minimal waste, though the backend sentence could have been spent on parameter meaning instead.

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 simple three-parameter extraction tool with no annotations and no output schema, the description covers what it produces and the platform/backend constraints. It leaves the two optional parameters undocumented and does not explain the accuracy/speed tradeoff, which is the main decision an agent faces when calling it.

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% across three parameters, so the description must compensate, yet it never mentions 'path', 'lang', or 'mode'. The language hint is only indirect ('Best for CJK + major European languages') and the accurate/fast 'mode' parameter is left entirely unexplained.

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?

The description states a specific verb and resource ('Extract tables from an image') plus the return format, and the 'Backend: vision' prefix distinguishes it from the paddle/xiaomi table siblings. It stops short of naming those siblings or stating explicitly what makes the vision backend the right pick.

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

Usage Guidelines3/5

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

'Best for CJK + major European languages' and 'Zero install on macOS' imply when this backend is a good fit, but there is no explicit when-to-use/when-not guidance and no reference to the alternative ocr_table_paddle or ocr_table_xiaomi tools listed among siblings.

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