Skip to main content
Glama

Create agent

create_agent

Create a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / safety_axioms}. Returns agent_id + initial graph summary.

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": {
      "genome": "<genome>"
    },
    "name": "create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
genomeYes{agent_name, purpose, initial_nodes, fitness_metrics, growth_rules?, safety_axioms?}.
request_idNoOptional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / genome / description
      Added value: +"{agent_name, purpose, initial_nodes, fitness_metrics, growth_rules?, safety_axioms?}."
    • addedInput schema / properties / request_id / description
      Added value: +"Optional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice."
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=false, so the mutation/safety profile is covered structurally. The description adds the return contract ('agent_id + initial graph summary') and validation constraints (unique nodes, >=1 fitness metric). It does not say what happens on duplicate agent_name or what a failed creation 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?

Two compact sentences, front-loaded with the verb and the input shape, and the return-value note is appended rather than buried. The brace-list formatting is dense but every token carries information; no filler sentences.

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?

With an output schema present, the description need not detail return values, and annotations cover the safety profile; what remains is adequate for a two-parameter mutation tool. The missing piece is domain context for the optional genome substructures, which the description names but never characterizes.

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?

Schema coverage is 100%, so the baseline would be 3, but the description adds constraints the schema does not express: initial_nodes must be unique and >=1, fitness_metrics must be >=1, and growth_rules/safety_axioms are optional. It still never explains what a safety_axiom or growth_rule actually contains, which is the heaviest semantic gap.

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?

States a specific verb+resource ('Create a developmental agent') and enumerates the genome fields it consumes, so the purpose is unambiguous. It does not name a contrasting sibling (e.g., describe_agent or get_agent), so differentiation is left to inference from the verb alone.

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 explicit when-to-use or when-not guidance, and no prerequisites are stated (e.g., whether a compute profile must exist first). An agent can infer it should call this before get_agent/delete_agent, but that inference comes from the verb, not the description.

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.