Skip to main content
Glama

Ocrspace

by io.github.pipeworx-io

Extract Text

extract_text
Read-onlyIdempotent

Extract text from an image or PDF via OCR — pass an image/PDF URL, get the recognized text. Useful for reading screenshots, scanned documents, receipts, signs. Engine 2 is best for most cases.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
engineNoOCR engine to use: 1, 2, or 3 (default 2). Engine 2 is best for most cases.
_apiKeyNoOptional — your own OCR.space API key for higher limits; omit to use the shared Pipeworx key.
is_tableNoSet true to improve layout detection for tables/receipts (default false).
languageNoLanguage code for OCR (default 'eng'). Examples: 'eng', 'fre', 'ger', 'spa'.
image_urlYesURL of an image or PDF to run OCR on.

TDQS

A3.8/5.0
Behavior2/5

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

Annotations already declare the tool as readOnly, idempotent, and non-destructive. Description adds minimal behavioral context, only noting the output is 'recognized text'. No mention of file size limits, supported formats, or processing time, which limits transparency beyond annotations.

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?

Two sentences, zero waste. The first sentence states core function and input/output; the second adds use cases and an engine recommendation. Essential information is front-loaded.

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 tool with 5 parameters, 1 required, and no output schema, the description covers purpose, use cases, and default engine. It could elaborate on the output format (e.g., plain text) or limitations, but is otherwise sufficient for an AI agent.

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 the baseline is 3. The description does not add new parameter details beyond the schema's own descriptions. It simply echoes the engine recommendation without clarifying format or constraints.

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?

Description clearly states the tool extracts text from images/PDFs via OCR using a URL. Verb 'extract' and resource 'text from image/PDF' are specific. No sibling tool performs similar OCR, so it is well-distinguished.

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?

Description lists concrete use cases (screenshots, scanned documents, receipts, signs) and recommends Engine 2 for most cases. It lacks explicit when-not-to-use guidance but the sibling list contains no competing OCR tools, so this is adequate.

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

All Ocrspace toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation2/5

Many tools serve overlapping purposes (multiple ask_pipeworx variants, several entity tools, multiple Polymarket edge tools), and while descriptions are detailed, an agent would struggle to quickly select the correct tool without careful reading.

Naming Consistency2/5

Naming conventions are mixed: some use verb_noun (ask_pipeworx, extract_text), others use noun_phrase (ai_visibility_check, bet_research, entity_profile), and no clear pattern dominates.

Tool Count3/5

32 tools is above the typical well-scoped range (3-15). While the broad domain of data query, prediction markets, memory, and subscriptions somewhat justifies the count, it still feels heavy and could benefit from consolidation.

Completeness4/5

The tool set covers most operations for its domain: data query (with multiple depth levels), memory CRUD, subscription lifecycle, and utilities like OCR and dependency scanning. Minor gaps exist (e.g., no direct modify operation), but overall it's fairly complete.

Resources