Skip to main content
Glama

create_agent

Create a new AI agent in the workspace. Use when a playbook step needs LLM reasoning (for example ticket classification or lead scoring). Model should use provider "gateway" and a model id from list_models. Optional skills[] and tools[] attach tenant skills and HTTP tools. Authoring details are in get_builder_guide topic "agent".

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>",
      "instructions": "<instructions>",
      "model": "<model>"
    },
    "name": "create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
modelYes
toolsNo
skillsNo
descriptionNo
instructionsYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=false and destructiveHint=false, so safety is covered; the description adds real behavioral constraints beyond that, notably that the provider must be 'gateway' and the model id must come from list_models, and that skills[]/tools[] bind existing tenant resources. It omits what happens on creation (whether the agent is immediately active, whether instructions are validated) and what is returned.

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?

Three compact sentences, front-loaded with the action and then the trigger condition, then the hard constraint, then the pointer to the authoring guide. The parenthetical examples for classification and lead scoring are mildly expendable but serve to disambiguate the usage condition.

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 mutation tool with no output schema and 0% parameter description coverage, the definition covers the distinctive constraints (provider gateway, model from list_models, resource attachment) but leaves the core instructions/name fields and the creation result unaddressed. Adequate to call correctly in the common case, incomplete for an agent that needs to know the outcome of the call.

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 0% and there is a nested model object, so the description must compensate; it does explain the model.provider/model.model constraint and the semantics of skills[] and tools[] as tenant skill and HTTP tool attachments. It adds nothing for name, description, or instructions, leaving a third of the parameters undocumented anywhere, which holds it to minimum-viable.

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?

States a specific verb and resource ('Create a new AI agent in the workspace') and immediately scopes it against the sibling family by tying it to playbook steps requiring LLM reasoning. An agent can distinguish it from create_playbook, create_skill, or create_tool without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

Gives a concrete trigger condition ('use when a playbook step needs LLM reasoning') plus example scenarios and routes to list_models for valid model ids and to get_builder_guide topic 'agent' for authoring details. It does not state when not to use it or what to use if the step needs no reasoning, so it falls short of full routing guidance.

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.

Resources