Skip to main content
Glama

read_image

Read-onlyIdempotent

Extract text from standalone image files (PNG, JPG, WebP, TIFF, BMP) using OCR to read image content instead of documents; supports multiple Tesseract languages.

Instructions

Extract text from a standalone image file (PNG, JPG, WebP, TIFF, BMP) using OCR. Use this when you need to read text from an image rather than a document; supports multiple languages via tesseract. Read-only.

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": {
      "filename": "<filename>"
    },
    "name": "read_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
filenameYesThe image filename to OCR (must be in the documents directory)
languageNoTesseract language code (default: DOCS_MCP_OCR_LANG, or "eng"). Use "spa" for Spanish, "fra" for French, etc.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.1
    • changedInput schema / properties / language / description
      Previous value: -"Tesseract language code (default: \"eng\"). Use \"spa\" for Spanish, \"fra\" for French, etc."New value: +"Tesseract language code (default: DOCS_MCP_OCR_LANG, or \"eng\"). Use \"spa\" for Spanish, \"fra\" for French, etc."
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the trailing 'Read-only.' adds nothing. The one genuine addition is the tesseract language dependency, which hints at an external engine and language-dependent accuracy, but nothing is said about OCR failure modes, empty results, or unsupported/garbled text.

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 sentences, tightly front-loaded with the verb and accepted formats, then the disambiguation rule. The closing 'Read-only.' is filler given the readOnlyHint annotation, a small but real piece of redundancy.

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?

For a simple two-parameter read tool with full schema coverage, rich annotations, and no output schema, the description covers what it does, on what inputs, and when to prefer it. The location constraint (documents directory) lives in the schema, so its absence here is not a gap; return shape is implied by 'extract text'.

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 description coverage is 100%, so both parameters are already documented, including the language default and code examples. The description only reinforces 'multiple languages via tesseract' without adding format, precedence, or fallback behavior beyond the schema. Baseline 3 applies.

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 ('Extract text from a standalone image file') plus the supported formats (PNG, JPG, WebP, TIFF, BMP) and the mechanism (OCR). It also marks the boundary against document tools ('rather than a document'), so an agent can separate it from read_document and ocr_document without opening any schema.

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?

Explicit usage condition is given: use it when the input is an image file rather than a document. That is a real routing rule, but it never names the sibling it competes with (ocr_document) or states what to do for images embedded in documents, so the alternative is implied rather than spelled out.

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