Skip to main content
Glama

Read the text in an image (OCR)

extract_text
Read-onlyIdempotent

Read printed text from a scan, a screenshot or a photo of a page. Languages: eng (English) and slv (Slovenian). Returns the text and the engine's confidence; below about 60 the text needs checking.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "extract_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_urlNoPublic http(s) address of the image. Use this or image_base64.
languagesNoDefault ["eng"].
image_base64NoThe image file's bytes, base64-encoded. Use for a local file, e.g. one in the repository.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, so the description rightly spends its words on the things annotations cannot say: the supported languages and that the result includes a confidence value, with the practical threshold ('below about 60 the text needs checking'). It stops short of describing how confidence is returned or failure modes.

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?

Three short sentences, front-loaded with what is read and from what inputs, then languages, then the return and its caveat. No filler.

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

Completeness4/5

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

With no output schema, the description does the needed work of naming the return values (text and confidence) and giving the confidence threshold. Remaining gap: nothing explains the mutual exclusivity of the two image inputs or what happens if neither is provided.

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 coverage is 100% and every parameter is already documented, so the description adds little: the eng/slv language values merely repeat the schema enum. It also never clarifies that at least one of image_url or image_base64 must be supplied, despite zero required parameters.

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 ('Read printed text from a scan, a screenshot or a photo of a page'), which clearly separates it from the sibling image tools (convert_image, inspect_image, upscale_image) that manipulate rather than transcribe images.

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 mention of 'printed text' and concrete input types (scan, screenshot, photo of a page) implies usage and implicitly excludes handwriting, but there is no explicit when-to-use/when-not guidance or routing against alternatives such as inspect_image.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources