Skip to main content
Glama

Фото в текст

image_to_text

Распознаёт текст на фото и картинках (OCR): текст всех фото — в один TXT или DOCX. Цена — как у ocr_pdf: одна единица за каждые 10 фото (или 10 МБ); цена единицы — get_balance. file_urls: публичные URL фото (JPG, PNG, WEBP, HEIC, TIFF, BMP). languages: rus, eng, deu, fra; по умолчанию ["rus", "eng"]. format: txt (по умолчанию, строки как на фото) | docx (абзацы).

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_urls": "<file_urls>"
    },
    "name": "image_to_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNotxt
file_urlsYes
languagesNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Beyond annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the cost model (one unit per 10 photos or 10 MB, unit price via get_balance) and the aggregation behavior of merging all photos into one output file. It does not explain how the resulting file is delivered, nor any limit on number of URLs.

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 and output are front-loaded, then pricing, then per-parameter notes — a sensible order with no filler. The pricing sentence is slightly tangential to tool selection but is genuine decision-relevant information, so it earns its place.

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?

An output schema exists, so return structure need not be described, and the description still tells the agent the result is one combined TXT/DOCX. Remaining gaps are minor: how the file is returned/downloaded and any cap on the number of photo URLs.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does it: file_urls is constrained to public JPG/PNG/WEBP/HEIC/TIFF/BMP URLs, languages enumerates rus/eng/deu/fra with the default ["rus","eng"], and format distinguishes txt (line layout preserved) from docx (paragraphs) with txt as default.

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?

The first sentence names a specific operation (OCR of text in photos and images) and the concrete output shape (all photos' text merged into a single TXT or DOCX). This cleanly separates it from ocr_pdf, which handles PDFs, and from pdf_to_txt, which handles text extraction from PDFs.

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?

The description makes the applicable input type explicit (photos as public URLs) and references ocr_pdf directly for pricing, so the agent can infer that PDF input belongs to ocr_pdf. There is no explicit exclusion statement like 'do not use for PDFs' and no prerequisites beyond 'public URL'.

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.