Skip to main content
Glama
Coval MCP Server

Coval MCP Server

Official
by coval-ai

Create agent

create_agent

Create a new agent configuration by defining its display name and model type, plus optional prompt, endpoint, metadata, or phone number for voice, chat, SMS, or WebSocket agents.

Instructions

Create a new agent configuration with a model type and connection details.

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": {
      "display_name": "<display_name>",
      "model_type": "<model_type>"
    },
    "name": "create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptNoSystem prompt or instructions for the agent
endpointNoWebhook or WebSocket endpoint URL
metadataNoCustom metadata for the agent
model_typeYesType of agent: MODEL_TYPE_VOICE, MODEL_TYPE_CHAT, MODEL_TYPE_SMS, etc.
display_nameYesHuman-readable name for the agent
phone_numberNoPhone number for voice agents (E.164 format)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / metadata / propertyNames
      Added value: +{
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare that this is a non-readonly, non-destructive, non-idempotent, closed-world mutation, so the safety profile does not need to come from the description. The description adds only that an agent is configured 'with a model type and connection details', without disclosing whether the new agent is immediately active, what identifier is returned, or which fields become required depending on model_type. With annotations covering the mutation semantics, this is the minimum viable level.

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?

It is a single front-loaded sentence with no filler or repetition. It is efficient, though the brevity comes at the cost of the behavioral context noted elsewhere.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter mutation with a nested metadata object and a model_type enum that drives conditional requirements (e.g., phone_number 'for voice agents'), the description says nothing about those dependencies or about what the call returns. With no output schema, some statement of the returned agent identifier would have been valuable. The result is under-specified for the tool's complexity.

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 parameter (display_name, model_type, prompt, endpoint, metadata, phone_number) is already documented in the input schema. The description mentions model_type and connection details but adds no syntax, format, or conditional logic beyond what the schema states, so baseline 3 applies.

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 agent configuration'), which clearly separates it from get_agent, list_agents, and update_agent. It does not explicitly name siblings, but the create vs. read/update distinction is unambiguous from the verbs 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 guidance on when to use this tool rather than create_run or update_agent, nor any stated preconditions (e.g., whether an agent must exist before a run can be created). The agent is left to infer usage entirely.

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