Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_agents_create

Create an autonomous agent definition with a system prompt, goal template, tool permissions, and LLM configuration so agents can run tasks and act on your behalf.

Instructions

Create a new autonomous agent definition with system prompt, goal template, tool permissions, and LLM config

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": "kernel_agents_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesAgent name
roleNo'manager' to allow this agent to spawn/update/delete other agents; 'worker' (default) cannot.
modelNoSpecific model name (default: provider default)
flow_idNoAssign agent to a flow/department by ID
providerNoLLM provider: claude, openai, lmstudio (default: system default)
timeout_msNoExecution timeout in ms (default: 300000)
descriptionNoWhat this agent does
denied_toolsNoBlacklist of tool names to exclude
allowed_toolsNoWhitelist of tool names (empty = all tools)
goal_templateNoGoal template with {{variables}} for dynamic goals
system_promptNoCustom system prompt for the LLM
max_iterationsNoMax tool-use loop iterations (default: 15)
__caller_agent_idNo[internal] injected by the agent executor when this tool is invoked from an agent run. Not meant to be set by external callers.
show_on_dashboardNoShow last flow result as a widget on dashboard home

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description bears the full behavioral burden, yet it says nothing about persistence, permissions or auth requirements, whether creation is idempotent, or what happens on duplicate names. It also omits the most consequential behavior: that setting role='manager' grants the new agent the ability to spawn/update/delete other agents — a privilege-escalation fact only visible in the schema.

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?

A single front-loaded sentence with no filler; the verb and resource lead. It is efficient, though the brevity is part of why behavioral gaps remain.

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?

For a 14-parameter creation tool with no annotations and no output schema, the description is thin: it does not indicate what is returned (agent ID?), whether the agent is enabled immediately, or the significance of the manager role. The rich schema compensates for per-field meaning, but not for lifecycle and side-effect context an agent needs before mutating state.

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 description coverage is 100%, so every one of the 14 parameters is already documented in the schema, including defaults for timeout_ms, max_iterations, provider, and the allowed/denied tool semantics. The description merely restates a subset of those fields at a higher level and adds no format, constraint, or interaction detail (e.g. allowed_tools vs denied_tools precedence).

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 states a specific verb and resource ('Create a new autonomous agent definition') and enumerates the main configuration surfaces (system prompt, goal template, tool permissions, LLM config), which separates it from read/maintenance siblings like kernel_agents_list or kernel_agents_history. It does not explicitly contrast itself with adjacent creation tools such as kernel_agents_flows_create, so it stops 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 Guidelines2/5

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

There is no statement of when to use this versus alternatives, no prerequisites (e.g. must a flow exist first?), and no guidance on whether the created agent is immediately active or needs a trigger/flow assignment. Usage is only implied by the word 'create'.

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

Deploy Server

Other Tools