Skip to main content
Glama

spix_call_summary

Generate AI summaries of phone calls using a session ID to extract key insights from conversations.

Instructions

Get AI-generated call summary

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_idYesCall session ID

Implementation Reference

  • The function `create_tool_handler` acts as the generic handler for all MCP tool calls (including `spix_call_summary`), resolving the tool name to a `CommandSchema` and dispatching it to the appropriate API endpoint.
    async def create_tool_handler(
        session: McpSessionContext,
        tool_name: str,
        arguments: dict,
    ) -> list:
        """Execute an MCP tool call by dispatching to the backend API.
    
        This function:
        1. Resolves the tool name to a command schema
        2. Validates session scope (playbook access, channel access)
        3. Builds the API request
        4. Dispatches to the backend
        5. Returns the response as MCP TextContent
    
        Args:
            session: The MCP session context for scope validation.
            tool_name: The MCP tool name (e.g., "spix_playbook_create").
            arguments: The tool arguments from the MCP client.
    
        Returns:
            List containing a single TextContent with the JSON response.
        """
        # Import here to avoid circular imports and handle missing mcp package
        try:
            from mcp.types import TextContent
        except ImportError:
            # Fallback for when mcp is not installed
            class TextContent:  # type: ignore[no-redef]
                def __init__(self, type: str, text: str) -> None:
                    self.type = type
                    self.text = text
    
        # Resolve tool name to schema
        schema = get_schema_by_tool_name(tool_name)
        if not schema:
            return [
                TextContent(
                    type="text",
                    text=orjson.dumps(
                        {"ok": False, "error": {"code": "unknown_tool", "message": f"Unknown tool: {tool_name}"}}
                    ).decode(),
                )
            ]
    
        # Validate tool access (not disabled)
        try:
            session.validate_tool_access(schema.path)
        except Exception as e:
            from spix_mcp.session import McpScopeError
    
            if isinstance(e, McpScopeError):
                return [TextContent(type="text", text=orjson.dumps({"ok": False, "error": e.to_dict()}).decode())]
            raise
    
        # Validate channel access if applicable
        channel = infer_channel_from_tool(schema.path)
        if channel:
            try:
                session.validate_channel_access(channel)
            except Exception as e:
                from spix_mcp.session import McpScopeError
    
                if isinstance(e, McpScopeError):
                    return [TextContent(type="text", text=orjson.dumps({"ok": False, "error": e.to_dict()}).decode())]
                raise
    
        # Handle playbook_id: validate and apply default
        playbook_id = arguments.get("playbook_id")
        try:
            effective_playbook = session.validate_playbook_access(playbook_id)
            if effective_playbook and not playbook_id:
                # Apply default playbook
                arguments["playbook_id"] = effective_playbook
        except Exception as e:
            from spix_mcp.session import McpScopeError
    
            if isinstance(e, McpScopeError):
                return [TextContent(type="text", text=orjson.dumps({"ok": False, "error": e.to_dict()}).decode())]
            raise
    
        # Build endpoint URL with path parameters
        endpoint, remaining_args = build_endpoint_url(schema, arguments)
    
        # Dispatch to backend API
        client = session.client
        method = schema.http_method.lower()
    
        if method == "get":
            response = await asyncio.to_thread(client.get, endpoint, params=remaining_args if remaining_args else None)
        elif method == "post":
            response = await asyncio.to_thread(client.post, endpoint, json=remaining_args if remaining_args else None)
        elif method == "patch":
            response = await asyncio.to_thread(client.patch, endpoint, json=remaining_args if remaining_args else None)
        elif method == "delete":
            response = await asyncio.to_thread(client.delete, endpoint, params=remaining_args if remaining_args else None)
        else:
            response = await asyncio.to_thread(client.get, endpoint)
    
        # Build response envelope
        envelope: dict = {"ok": response.ok, "meta": response.meta}
        if response.ok:
            envelope["data"] = response.data
            if response.pagination:
                envelope["pagination"] = response.pagination
            if response.warnings:
                envelope["warnings"] = response.warnings
        else:
            envelope["error"] = response.error
    
        return [TextContent(type="text", text=orjson.dumps(envelope).decode())]
  • The schema definition for the `call.summary` command (which corresponds to the `spix_call_summary` tool name via the `spix_` + `_` conversion logic in `tools.py`).
        path="call.summary",
        cli_usage="spix call summary <session_id>",
        http_method="GET",
        api_endpoint="/calls/{session_id}/summary",
        mcp_expose="tool",
        mcp_profile="safe",
        description="Get AI-generated call summary",
        positional_args=[
            CommandParam("session_id", "string", required=True, description="Call session ID"),
        ],
    ),
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Get AI-generated call summary,' which implies a read-only operation, but doesn't mention authentication needs, rate limits, response format, or potential errors. This leaves significant gaps in understanding how the tool behaves in practice.

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?

The description is a single, efficient sentence with no wasted words. It's front-loaded with the core purpose and appropriately sized for a simple tool, making it easy to parse quickly.

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

Completeness2/5

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

For a tool with no annotations and no output schema, the description is insufficient. It lacks details on what the summary contains, how it's structured, or any behavioral traits like error handling. Given the complexity implied by 'AI-generated,' more context is needed to guide the agent effectively.

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?

The input schema has 100% description coverage, with the parameter 'session_id' documented as 'Call session ID.' The description doesn't add any meaning beyond this, such as format examples or where to obtain the ID. Given the high schema coverage, a baseline score of 3 is appropriate as the schema does the heavy lifting.

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

Purpose3/5

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

The description 'Get AI-generated call summary' clearly states the action (get) and resource (call summary), but it's vague about what a 'call summary' entails and doesn't differentiate from sibling tools like spix_call_show or spix_call_transcript. It specifies 'AI-generated' which adds some specificity, but overall remains general.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like spix_call_show or spix_call_transcript. The description implies it retrieves a summary, but doesn't specify prerequisites, context, or exclusions, leaving the agent to guess based on tool names alone.

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/Spix-HQ/spix-mcp'

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