Skip to main content
Glama

agents_create

Create a new AI agent in the workspace.

Execution modes:

  • ai_assisted (default): Two-phase AI — fast pre-classifier (Haiku) for keyword filtering and simple replies, then full AI with tools for complex messages.

  • agentic: Autonomous multi-step agent with planning and tool execution.

  • rule_based: Simple pattern matching without AI.

Keyword filtering is available in ai_assisted mode via keywords in trigger conditions (free, deterministic) and/or auto_reply_rules (LLM-based) set through agents.update.

Pass prompt_text for the agent's instructions (stored inline on the agent) or prompt_id to link an existing prompt row, not both.

Tools: a new agent starts with the standard tool set (knowledge base lookup, replying, lead capture, reading files, handoff, plus the default voice-call tools). Pass allowed_tools to replace that set.

From a template: pass template (e.g. 'dm-auto-reply') to create the agent AND its built-in trigger in one call — deterministic, no need to add a trigger separately. When template is set, name/text_engine/send_mode come from the template.

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": {
      "name": "<name>"
    },
    "name": "agents_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesName of the AI agent (1-100 characters)
modelNoLLM the agent runs on. OMIT to use the platform default (deepseek-v4-flash-nothink). Applied right after creation so you don't need a follow-up agents_update.
runtimeNoFor a claude_channels (Session) agent: what its session runs on: 'claude', 'codex', or 'acp' (another agent, named in acp_agent). Codex and acp only in a workspace whose sessions run on the DialogBrain server; fixed once the agent has a session there. OMIT for 'claude'.
templateNoOptional template slug to instantiate the agent + its built-in trigger from (deterministic). Use 'dm-auto-reply' for the customer DM auto-reply agent (incoming DM trigger, draft mode). When set, the trigger comes from the template — you don't need agents.trigger_create. OMIT to create a plain agent (no template).
acp_agentNoFor runtime 'acp': which agent the session runs on, 'cursor' or 'antigravity'. It must be installed on the server that runs this workspace's sessions (refused in words otherwise). Required with runtime 'acp'; OMIT otherwise.
prompt_idNoID of the prompt to assign to this agent
send_modeNoDefault send mode: 'auto' or 'draft'. OMIT to use 'draft' (the default).
codex_modelNoFor runtime 'codex': the model its turns run on (default gpt-6.1-sol). A model DialogBrain has no price for is refused. OMIT for the default.
descriptionNoOptional description of what this agent does
prompt_textNoThe agent's instructions, stored inline on the agent (this is what drives how it replies). Works with or without `template`; no separate prompts tool needed. Write it from the business to its customers.
remote_toolNoOnly for text_engine='external_agent': the workspace integration tool that starts the remote agent, e.g. 'ext42_run_routine' (list them with integrations.search_tools). On each trigger DialogBrain calls it once with the event, the agent's instructions and the ids to answer with; the remote agent replies through the DialogBrain MCP tools (messages.send, tasks.comment, agents.task_complete). The endpoint and its secret belong to the integration, not to the agent.
text_engineNoText-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), 'claude_channels', or 'external_agent' (the run is handed to an agent outside DialogBrain; needs remote_tool). Voice is derived from triggers, not engine. OMIT to use the default ('agentic').
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
allowed_toolsNoExplicit allow-list of tool IDs the agent may call on triggered runs (e.g. ['knowledge.query', 'messages.send']). OMIT to give the agent the standard set: knowledge.query, messages.send, contacts.capture_lead, files.read, agent.handoff (plus the default voice-call tools). When passed, the list REPLACES the standard set entirely — include 'knowledge.query' for an agent that must answer from its knowledge base, or the model has no such tool and tends to imitate the call in its reply text. An empty list leaves the agent with no tools.
max_iterationsNoHard cap on agentic-loop turns per run (1-50). OMIT for the default (10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / acp_agent
      Added value: +{
      +  "description": "For runtime 'acp': which agent the session runs on, 'cursor' or 'antigravity'. It must be installed on the server that runs this workspace's sessions (refused in words otherwise). Required with runtime 'acp'; OMIT otherwise.",
      +  "type": "string"
      +}
    • changedInput schema / properties / runtime / description
      Previous value: -"For a claude_channels (Session) agent: what its session runs on, 'claude' or 'codex'. Codex only in a workspace whose sessions run on the DialogBrain server; fixed once the agent has a session there. OMIT for 'claude'."New value: +"For a claude_channels (Session) agent: what its session runs on: 'claude', 'codex', or 'acp' (another agent, named in acp_agent). Codex and acp only in a workspace whose sessions run on the DialogBrain server; fixed once the agent has a session there. OMIT for 'claude'."
    • changedInput schema / properties / runtime / enum
      Previous value: -[
      -  "claude",
      -  "codex"
      -]New value: +[
      +  "claude",
      +  "codex",
      +  "acp"
      +]
  2. Changed2 schema fields changed
    • addedInput schema / properties / codex_model
      Added value: +{
      +  "description": "For runtime 'codex': the model its turns run on (default gpt-6.1-sol). A model DialogBrain has no price for is refused. OMIT for the default.",
      +  "type": "string"
      +}
    • addedInput schema / properties / runtime
      Added value: +{
      +  "description": "For a claude_channels (Session) agent: what its session runs on, 'claude' or 'codex'. Codex only in a workspace whose sessions run on the DialogBrain server; fixed once the agent has a session there. OMIT for 'claude'.",
      +  "enum": [
      +    "claude",
      +    "codex"
      +  ],
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "claude-haiku-4-5-20251001",
      -  "claude-opus-4-6",
      -  "claude-sonnet-4-6",
      -  "claude-sonnet-5",
      -  "dashscope-glm-5.2",
      -  "dashscope-glm-5.2-nothink",
      -  "deepseek-v4-flash",
      -  "deepseek-v4-flash-nothink",
      -  "gpt-4.1",
      -  "gpt-4.1-mini",
      -  "gpt-4.1-nano",
      -  "gpt-4o",
      -  "kimi-k2.6",
      -  "qwen-flash",
      -  "qwen-plus",
      -  "qwen3-vl-flash",
      -  "qwen3-vl-plus",
      -  "qwen3.6-flash",
      -  "qwen3.6-plus"
      -]New value: +[
      +  "claude-haiku-4-5-20251001",
      +  "claude-opus-4-6",
      +  "claude-sonnet-4-6",
      +  "claude-sonnet-5",
      +  "dashscope-glm-5.2",
      +  "dashscope-glm-5.2-nothink",
      +  "deepseek-v4-flash",
      +  "deepseek-v4-flash-nothink",
      +  "gpt-4.1",
      +  "gpt-4.1-mini",
      +  "gpt-4.1-nano",
      +  "gpt-4o",
      +  "kimi-k2.6",
      +  "qwen-flash",
      +  "qwen-plus",
      +  "qwen3-vl-plus",
      +  "qwen3.6-flash",
      +  "qwen3.6-plus"
      +]
  4. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
      +  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
      +  "type": "integer"
      +}
  5. Changed3 schema fields changed
    • addedInput schema / properties / remote_tool
      Added value: +{
      +  "description": "Only for text_engine='external_agent': the workspace integration tool that starts the remote agent, e.g. 'ext42_run_routine' (list them with integrations.search_tools). On each trigger DialogBrain calls it once with the event, the agent's instructions and the ids to answer with; the remote agent replies through the DialogBrain MCP tools (messages.send, tasks.comment, agents.task_complete). The endpoint and its secret belong to the integration, not to the agent.",
      +  "type": "string"
      +}
    • changedInput schema / properties / text_engine / description
      Previous value: -"Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), or 'claude_channels'. Voice is derived from triggers, not engine. OMIT to use the default ('agentic')."New value: +"Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), 'claude_channels', or 'external_agent' (the run is handed to an agent outside DialogBrain; needs remote_tool). Voice is derived from triggers, not engine. OMIT to use the default ('agentic')."
    • changedInput schema / properties / text_engine / enum
      Previous value: -[
      -  "rule_based",
      -  "agentic",
      -  "claude_channels"
      -]New value: +[
      +  "rule_based",
      +  "agentic",
      +  "claude_channels",
      +  "external_agent"
      +]
  6. Added
  7. Removed
  8. Changed2 schema fields changed
    • addedInput schema / properties / prompt_text
      Added value: +{
      +  "description": "Only with `template`: the agent's persona/instructions, stored inline on the agent (drives how it replies). No separate prompts tool needed.",
      +  "type": "string"
      +}
    • addedInput schema / properties / template
      Added value: +{
      +  "description": "Optional template slug to instantiate the agent + its built-in trigger from (deterministic). Use 'dm-auto-reply' for the customer DM auto-reply agent (incoming DM trigger, draft mode). When set, the trigger comes from the template — you don't need agents.trigger_create. OMIT to create a plain agent (no template).",
      +  "enum": [
      +    "dm-auto-reply"
      +  ],
      +  "type": "string"
      +}
  9. Changed1 schema field changed
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "deepseek-chat",
      -  "deepseek-reasoner",
      -  "gpt-4.1",
      -  "gpt-4.1-mini",
      -  "gpt-4.1-nano",
      -  "gpt-4o",
      -  "claude-haiku-4-5-20251001",
      -  "claude-sonnet-4-6",
      -  "claude-opus-4-6",
      -  "kimi-k2.6"
      -]New value: +[
      +  "deepseek-chat",
      +  "deepseek-reasoner",
      +  "gpt-4.1",
      +  "gpt-4.1-mini",
      +  "gpt-4.1-nano",
      +  "gpt-4o",
      +  "claude-haiku-4-5-20251001",
      +  "claude-sonnet-4-6",
      +  "claude-sonnet-5",
      +  "claude-opus-4-6",
      +  "kimi-k2.6"
      +]
  10. Changed3 schema fields changed
    • addedInput schema / properties / allowed_tools
      Added value: +{
      +  "description": "Explicit allow-list of tool IDs the agent may call on triggered runs (e.g. ['workbench.run_python', 'messages.send']). OMIT to use system defaults. Applied right after creation.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / max_iterations
      Added value: +{
      +  "description": "Hard cap on agentic-loop turns per run (1-50). OMIT for the default (10).",
      +  "type": "integer"
      +}
    • addedInput schema / properties / model
      Added value: +{
      +  "description": "LLM the agent runs on. OMIT to use the platform default (deepseek-chat). Applied right after creation so you don't need a follow-up agents_update.",
      +  "enum": [
      +    "deepseek-chat",
      +    "deepseek-reasoner",
      +    "gpt-4.1",
      +    "gpt-4.1-mini",
      +    "gpt-4.1-nano",
      +    "gpt-4o",
      +    "claude-haiku-4-5-20251001",
      +    "claude-sonnet-4-6",
      +    "claude-opus-4-6",
      +    "kimi-k2.6"
      +  ],
      +  "type": "string"
      +}
  11. Changed1 schema field changed
    • changedInput schema / properties / text_engine / description
      Previous value: -"Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), or 'claude_channels'. Voice is derived from triggers, not engine."New value: +"Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), or 'claude_channels'. Voice is derived from triggers, not engine. OMIT to use the default ('agentic')."
  12. Changed2 schema fields changed
    • removedInput schema / properties / execution_mode
      Removed value: -{
      -  "description": "Execution mode: 'rule_based', 'ai_assisted' (default), 'agentic', 'claude_channels', or 'voice'. OMIT to use 'ai_assisted'.",
      -  "enum": [
      -    "rule_based",
      -    "ai_assisted",
      -    "agentic",
      -    "claude_channels",
      -    "voice"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / properties / text_engine
      Added value: +{
      +  "description": "Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), or 'claude_channels'. Voice is derived from triggers, not engine.",
      +  "enum": [
      +    "rule_based",
      +    "ai_assisted",
      +    "agentic",
      +    "claude_channels"
      +  ],
      +  "type": "string"
      +}
  13. Changed2 schema fields changed
    • addedInput schema / properties / execution_mode
      Added value: +{
      +  "description": "Execution mode: 'rule_based', 'ai_assisted' (default), 'agentic', 'claude_channels', or 'voice'. OMIT to use 'ai_assisted'.",
      +  "enum": [
      +    "rule_based",
      +    "ai_assisted",
      +    "agentic",
      +    "claude_channels",
      +    "voice"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / text_engine
      Removed value: -{
      -  "description": "Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), or 'claude_channels'. Voice is derived from triggers, not engine.",
      -  "enum": [
      -    "rule_based",
      -    "ai_assisted",
      -    "agentic",
      -    "claude_channels"
      -  ],
      -  "type": "string"
      -}
  14. Changed2 schema fields changed
    • removedInput schema / properties / execution_mode
      Removed value: -{
      -  "description": "Execution mode: 'rule_based', 'ai_assisted' (default), 'agentic', 'claude_channels', or 'voice'. OMIT to use 'ai_assisted'.",
      -  "enum": [
      -    "rule_based",
      -    "ai_assisted",
      -    "agentic",
      -    "claude_channels",
      -    "voice"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / properties / text_engine
      Added value: +{
      +  "description": "Text-execution engine: 'rule_based', 'ai_assisted', 'agentic' (default), or 'claude_channels'. Voice is derived from triggers, not engine.",
      +  "enum": [
      +    "rule_based",
      +    "ai_assisted",
      +    "agentic",
      +    "claude_channels"
      +  ],
      +  "type": "string"
      +}
  15. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations mark this as a non-read-only, non-idempotent create, and the description adds real behavior on top: `model` is applied immediately so no follow-up agents_update is needed, new agents get the standard tool set (enumerated), and `allowed_tools` REPLACES that set entirely, with the concrete failure mode spelled out (the model 'tends to imitate the call in its reply text'). It does not cover name-collision behavior, whether creation can fail on permission grounds, or what the call returns.

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 lead sentence comes first, bullets break the modes into scannable lines, and the highest-risk constraint (allowed_tools replacement) gets its own paragraph. A few lines, such as the detailed description of what ai_assisted does internally, are more background than decision-relevant, but there is no 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 15-parameter create tool with no output schema, the description covers the risky decisions: template vs plain, tool allow-list replacement, prompt sourcing, and model application timing. It leaves out what the call returns (an agent id/object?) and whether `name` must be unique, which an agent would need to chain a follow-up create or reuse.

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?

Schema coverage is already 100%, so the baseline is 3; the description does add genuine meaning for cross-parameter rules (template precedence, prompt_text/prompt_id exclusivity, allowed_tools replacement semantics). However, it introduces a mode list that conflicts with the schema: it presents 'ai_assisted (default)' as an execution mode while the `text_engine` enum contains only rule_based/agentic/claude_channels/external_agent and declares 'agentic' the default, which can mislead an agent filling that field.

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 opening sentence states a specific verb and resource ('Create a new AI agent in the workspace') and the body scopes it further by enumerating execution modes and the template path. It also names the sibling actions it makes unnecessary ('you don't need agents.trigger_create', 'no separate prompts tool needed'), so an agent can place it against agents_update and agents_trigger_create without opening schemas.

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?

Explicit when-to-use branches are given: plain agent vs `template` instantiation, `prompt_text` vs `prompt_id` ('not both'), and default tool set vs an explicit `allowed_tools` override. It also flags the exclusion condition that matters operationally ('When `template` is set, name/text_engine/send_mode come from the template'), so the agent knows which inputs become inert.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.