flowforge-mcp

flowforge_create_assistant

Create a new voice assistant agent by name, then configure its system prompt, TTS/STT settings, model, and flow data to define how it talks and behaves.

Instructions

Create a new voice assistant (agent).

Only name is required. Provide system_prompt for a simple agent, or pass extra_config={'flow_data': {...}} for a flow-based agent. Voice and transcription are configured via tts_settings / stt_settings.

Args: params: See field descriptions. extra_config accepts any additional AssistantCreateRequest field verbatim.

Returns: The created assistant object (including its new ID) as JSON or Markdown.

Error Handling: Returns "Error: Validation failed..." (422) if fields are malformed.

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": {
      "params": "<params>"
    },
    "name": "flowforge_create_assistant"
  }
}

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, open-world write, so the safety profile is covered. The description adds value beyond that by disclosing the return shape (created object with new ID, in JSON or Markdown) and a concrete error contract (422 'Error: Validation failed...' for malformed fields). It does not warn that repeated calls create duplicate assistants, which the non-idempotent hint implies.

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?

Content is front-loaded and organized into Args/Returns/Error Handling blocks, so the agent can skim to what it needs. The Returns line partly duplicates the response_format schema description, but overall there is very little filler.

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?

For a create operation with rich nested schema and an output schema present, the description covers the essentials: required vs optional fields, the two agent-construction modes, the response format toggle, and the validation error path. The main remaining gap is duplicate-creation risk and what happens if a referenced mcp_server or flow_data is invalid.

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?

Although the reported coverage is 0%, that metric only reflects the top-level 'params' wrapper; the description still adds genuine meaning by explaining the two mutually exclusive creation modes (system_prompt vs extra_config.flow_data) and by framing extra_config as a verbatim escape hatch for unlisted AssistantCreateRequest fields. The pointer 'See field descriptions' correctly defers per-field detail to the schema. Voice/transcription settings are named but not given concrete shapes beyond what the schema already shows.

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 opening line states a specific verb and resource: 'Create a new voice assistant (agent).' That is unambiguous and clearly separates it from the read/update/delete assistant siblings. It does not, however, explicitly contrast with the nearest look-alikes such as flowforge_import_assistant or flowforge_assistant_lifecycle, so it falls short of a 5.

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 does supply real conditional guidance: 'Provide system_prompt for a simple agent, or pass extra_config={flow_data: {...}} for a flow-based agent,' which tells the agent which creation path to take. What is missing is guidance on when to prefer this tool over alternatives like import_assistant or assistant_lifecycle, so usage context is implied rather than fully stated.

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

Deploy Server