Skip to main content
Glama
team-telnyx

Telnyx MCP Server

Official
by team-telnyx

create_assistant

Create custom AI assistants with Telnyx telephony integration by configuring models, instructions, and tools for voice, messaging, and webhook capabilities.

Instructions

Create a new AI Assistant. The user will provide some details (sometimes detailed, sometimes vague) about the agent they want to create.

Args:
    name: Required. Name of the assistant. If not provided, will be generated based on context.
    model: Required. Model to use for the assistant. Defaults to meta-llama/Meta-Llama-3.1-70B-Instruct.
    instructions: Required. Core instructions or behaviors for the agent.
    description: Optional. A summary of the agent's purpose.
    tools: Optional. List of tools for the assistant, each containing:
        - type: Required. Type of tool ("function", "retrieval", "webhook",
        "hangup", "send_dtmf", "transfer").
        - function: Optional. For function tools, contains:
            - name: Required. Name of the function.
            - description: Optional. Description of the function.
            - parameters: Required. Parameters schema for the function.
        - retrieval: Optional. For retrieval tools, contains:
            - bucket_ids: Required. List of bucket IDs for retrieval.
            - max_num_results: Optional. Maximum number of results to retrieve.
        - webhook: Optional. For webhook tools, contains:
            - name: Required. The name of the tool.
            - description: Required. The description of the tool.
            - url: Required. The URL of the external tool to be called. This URL can be
              templated like: https://example.com/api/v1/{id}, where {id} is a
              placeholder for a value that will be provided by the assistant if
              path_parameters are provided with the id attribute.
            - method: Optional. The HTTP method to be used. Possible values:
              [GET, POST, PUT, DELETE, PATCH]. Default value: POST.
            - headers: Optional. Array of header objects with:
                - name: String name of the header.
                - value: String value of the header. Supports mustache templating.
                  e.g., Bearer {{#integration_secret}}test-secret{{/integration_secret}}.
                  Secrets can be found in `list_integration_secrets`
            - body_parameters: Optional. JSON Schema object describing the body parameters:
                - properties: Object defining the properties of the body parameters.
                - required: Array of strings listing required properties.
                - type: String. Possible value: "object".
            - path_parameters: Optional. JSON Schema object describing the path parameters:
                - properties: Object defining the properties of the path parameters.
                - required: Array of strings listing required properties.
                - type: String. Possible value: "object".
            - query_parameters: Optional. JSON Schema object describing the query parameters:
                - properties: Object defining the properties of the query parameters.
                - required: Array of strings listing required properties.
                - type: String. Possible value: "object".
        - hangup: Optional. For hangup tools, contains:
            - description: Optional. Description of the hangup function. Defaults to
              "This tool is used to hang up the call."
        - send_dtmf: Optional. For DTMF tools, contains an empty object. This tool
          allows sending DTMF tones during a call.
        - transfer: Optional. For transfer tools, contains:
            - targets: Required. Array of transfer targets, each with:
                - name: Optional. Name of the target.
                - to: Required. Destination number or SIP URI.
            - from: Required. Number or SIP URI placing the call.
            - custom_headers: Optional. Array of custom SIP headers, each with:
                - name: Required. Name of the header.
                - value: Required. Value of the header. Supports mustache templating.
    greeting: Optional. A short welcoming message. Will be generated if not provided.
    llm_api_key_ref: Optional. LLM API key reference.
    transcription: Optional. Transcription settings with:
        - model: Optional. Model to use for transcription.
    messaging_settings: Optional. Messaging settings with:
        - default_messaging_profile_id: Optional. Default messaging profile ID.
        - delivery_status_webhook_url: Optional. Webhook URL for delivery status updates.
    insight_settings: Optional. Insight settings with:
        - insight_group_id: Optional. Insight group ID.
    dynamic_variables_webhook_url: Optional. Dynamic variables webhook URL.
    dynamic_variables: Optional. Dynamic variables dictionary.

Returns:
    Dict[str, Any]: Response data

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
requestYes
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that the tool creates an assistant but does not mention any behavioral traits such as permissions required, whether the creation is idempotent, rate limits, or what happens on failure. The description focuses heavily on parameter details but lacks critical operational context for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

The description is overly verbose and poorly structured. It front-loads the purpose but then devolves into a lengthy, nested parameter documentation that belongs in the schema. Sentences like 'The user will provide some details...' are vague and do not earn their place. The text is bloated with implementation details that hinder quick understanding.

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 complexity (1 parameter with nested objects, no annotations, no output schema), the description is partially complete. It thoroughly documents parameters but lacks behavioral context, usage guidelines, and output details. For a creation tool with no structured safety or output information, this leaves gaps in operational understanding, though parameter coverage is strong.

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 input schema has 0% description coverage and only one parameter ('request') with no details, but the description compensates extensively. It provides detailed semantics for 15+ parameters (e.g., 'name', 'model', 'instructions', 'tools' with nested structures), explaining their purposes, optionality, defaults, and data types. This adds significant value beyond the minimal 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?

The description clearly states the purpose: 'Create a new AI Assistant.' It specifies the verb ('Create') and resource ('AI Assistant'), making the intent unambiguous. However, it does not explicitly distinguish this tool from its sibling 'update_assistant' or other creation tools like 'create_call_control_application', which slightly reduces clarity in context.

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?

The description provides no guidance on when to use this tool versus alternatives. It mentions that 'The user will provide some details (sometimes detailed, sometimes vague) about the agent they want to create,' but this is generic and does not specify prerequisites, constraints, or when to choose this over other tools like 'update_assistant' or 'get_assistant'. No explicit alternatives or exclusions 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/team-telnyx/telnyx-mcp-server'

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