Create a new agent by specifying a role and system prompt, with optional tool definitions. Add it to an orchestration workflow to assign asynchronous tasks and monitor results.
Spawn a new agent with the given role and system prompt
| Name | Required | Description | Default |
|---|---|---|---|
| tools | No | Optional list of tool definitions (OpenAI format) to make available to the agent | |
| role_name | Yes | Role name (e.g., 'coder') | |
| system_prompt | Yes | System prompt for the agent |
Changes observed during successful MCP inspections.
v0.3.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only mentions the action and inputs, but does not explain side effects (e.g., whether an agent is immediately active), resource implications, required permissions, or what happens on failure. For a creation tool this is a significant transparency gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, grammatically simple sentence with no filler words. It front-loads the primary verb and object. It is appropriately concise, though it could have used the brevity to include a hint about return values or lifecycle without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema and no annotations, the description leaves key operational details unstated: what the tool returns (presumably an agent identifier needed for later sibling calls), how the spawned agent is managed afterward, and any constraints on role_name or system_prompt. An agent cannot fully infer invocation success criteria or follow-up steps from this description alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters. The description adds no meaning beyond restating 'role' and 'system prompt' from the schema; the 'tools' parameter is left entirely to the schema. This meets the baseline for full coverage but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'spawn' and identifies the resource ('new agent'), plus the two key inputs (role and system prompt). This clearly distinguishes it from sibling tools like list_agents, stop_agent, and agent_status, though it does not explicitly name any alternative or contrast itself with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives, nor any conditions, prerequisites, or exclusions. The description simply states what it does without addressing the decision context among the many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.