ocrExtract text from an image file (OCR). 이미지 파일에서 텍스트를 추출해 전체 텍스트(full_text)를 반환합니다. 문서 사진, 스캔 이미지, 캡처 화면 등 범용 이미지에 사용합니다. [호출당 12포인트]
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg) (최대 50MB) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it as read-only, but the description adds useful non-obvious behavior: it returns the complete extracted text as 'full_text' and discloses the per-call cost of 12 points. This goes beyond the structured annotations, though it does not discuss error cases or what happens with unsupported input.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded with the core action, followed by usage context and cost. There is slight redundancy between the English sentence 'Extract text from an image file (OCR)' and the Korean sentence that repeats the same idea, which prevents a perfect conciseness score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter, read-only OCR tool with no output schema, the description covers what an agent needs: the action, the return shape (full_text), the intended image types, and the cost. The input parameter constraints are fully handled by the schema, so no critical information is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter, image_url, is already fully documented in the input schema with details about HTTPS URL, allowed MIME types, and the 50MB size limit. The description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource: 'Extract text from an image file (OCR)' and further clarifies it returns 'full_text'. It also positions itself for '범용 이미지' (general-purpose images) such as document photos, scans, and screenshots, which implicitly separates it from sibling OCR tools like ocr_identi* and identity_document_*. This makes the tool's purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to use it for '문서 사진, 스캔 이미지, 캡처 화면 등 범용 이미지', giving clear context for when this tool is appropriate. However, it does not explicitly state when not to use it or point to alternatives like the identity-document OCR siblings, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools target the same documents with unclear boundaries: identi_card_image1, ocr_identi1, and identity_document_id_card all accept a resident registration card image but differ in verification vs extraction vs masking, which agents will struggle to distinguish. The identi_card1-5 vs identi_card_image1-5 vs ocr_identi1-5 clusters are especially confusing, despite some helpful descriptions.
Naming is highly inconsistent: some tools use verb_noun (check_phone_valid, search_juso, pdf_merge), some are bare nouns (whois, nslookup, ocr, stt), and identity tools use three parallel schemes (identi_card1, identi_card_image1, ocr_identi1, identity_document_id_card) with no clear pattern. No single convention is followed across the toolset.
88 tools is an extreme count for a single MCP server, spanning identity verification, parcel tracking, LLM chat, image generation, PDF conversion, TTS, and network lookups. This is an API marketplace dump rather than a focused toolset, and the number far exceeds any reasonable scope.
The server's scope is unbounded, so it has gaps everywhere: no video transcription shortcut, no PDF splitting, no batch cancellation for images (only TTS), and identity clusters lack clear differentiation between verify/extract/mask workflows. Some subdomains like TTS have a full lifecycle, but overall the coverage is scattered and incomplete for the implied breadth.