Skip to main content
Glama

ocr_image

Read-only

Extract text and language from an image URL or cached image ID; returns recognized text with confidence and coordinates. Does not accept local paths or base64.

Instructions

OCR 图片(服务端,需图片 URL 或已缓存的图片 file_id) 替换为实际可访问的图片地址或已缓存图片标识;不支持本地路径和 base64。 Returns: { texts, language }:识别文本数组(含置信度与坐标)与识别语言。

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": {
      "image": "<image>"
    },
    "name": "ocr_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; the description adds server-side execution and result shape. However, it contains confusing boilerplate instructing the caller to 'replace with the actual accessible image address', which reads like template residue rather than behavior, and it says nothing about size limits, cost, 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Compact and front-loaded with the key constraint, and the return shape is appended usefully. But the placeholder-style sentence about substituting a real image address is noise that could mislead an agent into thinking it must rewrite something.

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 one parameter, no output schema, and a simple read-only operation, the description covers input form, exclusions, and the return structure ({ texts, language } with confidence and coordinates). Missing only operational limits such as file size, formats, or supported languages beyond the reported language field.

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

Parameters4/5

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

Schema coverage is 0% for the single `image` parameter, so the description carries the burden — and it does: it specifies the accepted forms (URL or cached file_id) and explicitly rules out local paths and base64. That is meaningful semantics well beyond a bare string schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: server-side OCR of an image, with the required input form (image URL or cached file_id). It implicitly separates itself from sibling image helpers (get_image, view_image) by being the OCR path, but never names an alternative, so it stops short of full sibling differentiation.

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?

Gives clear preconditions — an accessible image URL or a cached file_id is required, local paths and base64 are rejected — which lets an agent decide upfront whether it can call the tool. It does not explicitly state when to prefer a different tool (e.g. a viewer or uploader), so no explicit exclusion routing.

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

Deploy Server

Other Tools