Skip to main content
Glama
wasintoh

line-oa-mcp-ultimate

by wasintoh

Design LINE Imagemap (Rich Message)

line_design_imagemap
Read-onlyIdempotent

Construct and validate a LINE Imagemap message JSON with tappable areas and optional video. Pre-host images at a public HTTPS URL; this tool builds the message object for sending via line_send_message.

Instructions

Build a validated Imagemap message (LINE OA Manager calls this a "Rich Message") and return it as JSON, ready to hand to line_send_message. DESIGN ONLY — this never calls the LINE API; it just builds + validates the message object.

Image hosting (read carefully):

  • LINE has NO imagemap-image upload API. You MUST pre-host the image yourself at a public HTTPS base_url.

  • At send time LINE fetches sized variants: ${base_url}/1040, /700, /460, /300, /240. Host all of them (or a server that serves the right size per suffix).

  • baseSize.width is always forced to 1040. You only provide base_height (the image height when width = 1040). All area coordinates are px on that 1040-wide canvas.

Args:

  • base_url: HTTPS base URL of the hosted image set (≤1000 chars).

  • alt_text: Fallback text (1..400 chars).

  • base_height: Integer image height at width 1040.

  • areas: ≥1 tappable area, each { bounds: { x, y, width, height (ints) }, action: { type:"uri", uri, label? } | { type:"message", text, label? } }. Areas must fit inside 1040 × base_height.

  • video: optional { original_content_url, preview_image_url, area, external_link? }.

Returns: { message: , usage_hint: string }

Composability:

  • Build here → grab message → send via line_send_message (raw message passthrough).

Examples:

  • "Rich Message โปรโมชั่น ครึ่งบน-ครึ่งล่าง กดไปคนละลิงก์" → { base_url: "https://cdn.example.com/promo", alt_text: "โปรโมชั่นเดือนนี้", base_height: 1040, areas: [ { bounds: { x: 0, y: 0, width: 1040, height: 520 }, action: { type: "uri", uri: "https://shop.example.com/a" } }, { bounds: { x: 0, y: 520, width: 1040, height: 520 }, action: { type: "uri", uri: "https://shop.example.com/b" } } ] }

Errors:

  • base_url ต้องเป็น HTTPS → fix the URL scheme

  • พื้นที่เกินขอบรูป → an area's x+width or y+height exceeds 1040 × base_height

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
base_urlYesHTTPS base URL of the pre-hosted image set. LINE requests /1040 /700 /460 /300 /240 from it. No upload API — you must host the images yourself.
alt_textYesFallback text shown when the image can't render (≤400 chars).
base_heightYesImage height in px WHEN the width is 1040 (width is always forced to 1040).
areasYesAt least 1 tappable area. Bounds are px on the 1040-wide base; must stay in bounds.
videoNoOptional inline video that plays over part of the image.
Behavior5/5

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

Annotations indicate readOnlyHint, destructiveHint, idempotentHint. The description confirms no side effects and adds critical behavioral details: no upload API, the forced width of 1040, coordinate system, validation rules, and error messages. This goes well beyond what annotations provide.

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?

The description is well-structured with clear headings (Image hosting, Args, Returns, Composability, Examples, Errors) and front-loads the core purpose. It is somewhat lengthy but every section adds value. Minor reduction in redundancy could improve conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 parameters, nested objects, no output schema), the description covers purpose, usage, behavior, parameter details with examples, error messages, and composability. It provides enough information for an AI agent to build an imagemap message correctly without relying on an output schema.

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 100%, so baseline is 3. The description adds meaningful context beyond the schema, such as the image hosting requirements (LINE fetches sized variants from URLs), the forced width of 1040, and explicit error examples. However, some parameter details (e.g., video) are well-covered in schema, so the added value is strong but not exceptional.

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 description clearly states the verb 'Build' and resource 'validated Imagemap message', and explicitly distinguishes itself from sending tools like line_send_message with 'DESIGN ONLY — this never calls the LINE API'. It precisely defines what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: it is for design only, not API calls, and tells the agent to hand the output to line_send_message. It also explains when to use this tool vs alternatives by noting composability and that it never sends messages, differentiating from siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wasintoh/line-oa-mcp-ultimate'

If you have feedback or need assistance with the MCP directory API, please join our Discord server