Skip to main content
Glama

ocr_layout_vision

Extract text with layout analysis using Apple Vision OCR, returning text blocks with bounding boxes. Ideal for CJK and major European languages on macOS with no install required.

Instructions

Extract text with layout analysis. Returns blocks with bounding boxes.

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_layout_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

B3/5.0
Behavior2/5

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

With no annotations at all, the description carries the full behavioral burden. It usefully discloses that inference is on-device via GPU/ANE and requires macOS 10.15+, but says nothing about behavior on non-macOS hosts, whether language data must be downloaded, what happens with unsupported languages, or how failures surface.

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?

Purpose is front-loaded in the first sentence and backend characteristics are grouped cleanly in a second paragraph. Tight overall; "Zero install on macOS" is mildly redundant with "on-device" but earns its place as a deployment consideration.

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?

Output shape is partly described (blocks with bounding boxes) and backend traits are covered, which suits a no-output-schema tool. But with no annotations and 0% schema coverage, the definition leaves both parameters and error/platform behavior undocumented — an agent could pick this tool but would guess at `mode` and `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 `lang` (format/values) nor `mode` (only a default of "accurate", implying a faster alternative that is never named) is explained anywhere. Only `path` is implicitly covered by "Extract text". This is a real gap for a 3-parameter tool.

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?

"Extract text with layout analysis. Returns blocks with bounding boxes" gives a specific verb, resource, and output shape, and implicitly separates it from ocr_text_vision (plain text) and ocr_table_vision (tables). It never names those siblings explicitly, so the differentiation is inferred from the tool names rather than stated.

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?

The line "Best for CJK + major European languages" and "Zero install on macOS" implies when this backend is preferable, which is real usage signal. However, it never names the alternative (ocr_layout_paddle) or states when NOT to use this tool, leaving the backend choice to inference.

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