Skip to main content
Glama

send_images

Create Bluesky posts with up to 4 images, including text, alt descriptions, and optional features like replies or language tags.

Instructions

Send a post with multiple images (up to 4).

Args:
    ctx: MCP context
    text: Text content of the post
    images_data: List of base64-encoded image data (max 4)
    image_alts: Optional list of alt text for each image
    profile_identify: Optional handle or DID for the post author
    reply_to: Optional reply information dict with keys uri and cid
    langs: Optional list of language codes
    facets: Optional list of facets (mentions, links, etc.)

Returns:
    Status of the post creation

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
images_dataYes
image_altsNo
profile_identifyNo
reply_toNo
langsNo
facetsNo

Implementation Reference

  • The MCP tool handler for "send_images". This function is decorated with @mcp.tool() which registers it as an MCP tool. It validates input, decodes base64-encoded image data, and uses the authenticated Bluesky client to send a post with up to 4 images.
    @mcp.tool()
    def send_images(
        ctx: Context,
        text: str,
        images_data: List[str],
        image_alts: Optional[List[str]] = None,
        profile_identify: Optional[str] = None,
        reply_to: Optional[Dict[str, Any]] = None,
        langs: Optional[List[str]] = None,
        facets: Optional[List[Dict[str, Any]]] = None,
    ) -> Dict:
        """Send a post with multiple images (up to 4).
    
        Args:
            ctx: MCP context
            text: Text content of the post
            images_data: List of base64-encoded image data (max 4)
            image_alts: Optional list of alt text for each image
            profile_identify: Optional handle or DID for the post author
            reply_to: Optional reply information dict with keys uri and cid
            langs: Optional list of language codes
            facets: Optional list of facets (mentions, links, etc.)
    
        Returns:
            Status of the post creation
        """
        try:
            bluesky_client = get_authenticated_client(ctx)
    
            # Verify we have 1-4 images
            if not images_data:
                return {
                    "status": "error",
                    "message": "At least one image is required",
                }
    
            if len(images_data) > 4:
                return {
                    "status": "error",
                    "message": "Maximum of 4 images allowed",
                }
    
            # Decode all images
            images_bytes = []
            for img_data in images_data:
                try:
                    image_bytes = base64.b64decode(img_data)
                    images_bytes.append(image_bytes)
                except Exception as e:
                    return {
                        "status": "error",
                        "message": f"Failed to decode image data: {str(e)}",
                    }
    
            # Send the post with images
            post_response = bluesky_client.send_images(
                text=text,
                images=images_bytes,
                image_alts=image_alts,
                profile_identify=profile_identify,
                reply_to=reply_to,
                langs=langs,
                facets=facets,
            )
    
            return {
                "status": "success",
                "message": "Post with images created successfully",
                "post_uri": post_response.uri,
                "post_cid": post_response.cid,
            }
        except Exception as e:
            error_msg = f"Failed to create post with images: {str(e)}"
            return {"status": "error", "message": error_msg}
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the action ('send a post') and image limits, but fails to disclose critical behavioral traits: whether this is a write operation (implied but not stated), authentication requirements, rate limits, error conditions, or what 'Status of the post creation' entails. The description is insufficient for a mutation tool with zero annotation coverage.

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 a clear purpose statement followed by organized parameter and return value sections. It's appropriately sized for a tool with 7 parameters, though some sentences could be more concise (e.g., 'Returns: Status of the post creation' is vague).

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

Completeness3/5

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

Given the tool's complexity (7 parameters, mutation operation) with no annotations and no output schema, the description is incomplete. While parameter semantics are well-covered, it lacks crucial behavioral context (authentication, side effects, error handling) and the return value description is too vague ('Status of the post creation'). For a mutation tool with this complexity, more completeness is needed.

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

Parameters5/5

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

The description provides comprehensive parameter semantics beyond the input schema, which has 0% description coverage. Each parameter is clearly explained with its purpose and constraints (e.g., 'images_data: List of base64-encoded image data (max 4)', 'facets: Optional list of facets (mentions, links, etc.)'). This fully compensates for the schema's lack of descriptions.

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 tool's purpose: 'Send a post with multiple images (up to 4).' This specifies the verb ('send'), resource ('post'), and a key constraint ('multiple images up to 4'), distinguishing it from sibling tools like 'send_post' (text-only) and 'send_image' (single image).

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

Usage Guidelines3/5

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

The description implies usage context through parameter descriptions (e.g., 'reply_to' for replying, 'profile_identify' for author specification), but lacks explicit guidance on when to use this tool versus alternatives like 'send_post' or 'send_image'. No when-not-to-use scenarios or prerequisites are mentioned.

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/gwbischof/bluesky-social-mcp'

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