Skip to main content
Glama

Patch MCP

start_agent_test

Idempotent

Run one isolated synthetic conversation against the active agent settings at the supplied revision. Outbound supports preset or custom fictional scenarios; inbound requires custom_scenario or scenario_description. Uses LiveKit test rooms and may consume AI usage. Never dials a phone number, publishes settings or invokes connected external tools.

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": {
      "number_id": "<number_id>",
      "revision": "<revision>",
      "scenario": "<scenario>",
      "direction": "<direction>",
      "request_id": "<request_id>"
    },
    "name": "start_agent_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
revisionYes
scenarioYes
directionYesoutbound
number_idYes
request_idYes
custom_scenarioNo
responder_outcomeNoAn outcome ID from list_test_scenarios, or custom fictional facts for the responder. Omit to use the first outcome.
scenario_descriptionNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / scenario_description
      Added value: +{
      +  "maxLength": 4000,
      +  "minLength": 10,
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": {},
      -    "propertyNames": {
      -      "type": "string"
      -    },
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": {},
      -    "properties": {
      -      "error": {
      -        "type": "string"
      -      },
      -      "message": {
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "error"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": {},
      -    "properties": {
      -      "message": {
      -        "type": "string"
      -      },
      -      "next_action": {
      -        "type": "string"
      -      },
      -      "operation_id": {
      -        "type": "string"
      -      },
      -      "status": {
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "operation_id",
      -      "status"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "createdAt": {
      +        "type": "string"
      +      },
      +      "direction": {
      +        "enum": [
      +          "inbound",
      +          "outbound"
      +        ],
      +        "type": "string"
      +      },
      +      "endedAt": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "id": {
      +        "maxLength": 200,
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "operation_id": {
      +        "type": "string"
      +      },
      +      "result": {},
      +      "revision": {
      +        "maximum": 9007199254740991,
      +        "minimum": 0,
      +        "type": "integer"
      +      },
      +      "scenario": {
      +        "enum": [
      +          "delivery",
      +          "reservation",
      +          "copay",
      +          "custom"
      +        ],
      +        "type": "string"
      +      },
      +      "simulatedMessage": {},
      +      "startedAt": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "state": {
      +        "enum": [
      +          "starting",
      +          "running",
      +          "completed",
      +          "stopped",
      +          "failed",
      +          "timeout",
      +          "interrupted"
      +        ],
      +        "type": "string"
      +      },
      +      "title": {
      +        "type": "string"
      +      },
      +      "transcript": {
      +        "items": {
      +          "additionalProperties": {},
      +          "propertyNames": {
      +            "type": "string"
      +          },
      +          "type": "object"
      +        },
      +        "type": "array"
      +      },
      +      "transcriptExpired": {
      +        "type": "boolean"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "state",
      +      "scenario",
      +      "direction",
      +      "revision",
      +      "title",
      +      "startedAt",
      +      "createdAt",
      +      "endedAt",
      +      "transcriptExpired",
      +      "transcript",
      +      "result",
      +      "simulatedMessage"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "error": {
      +        "type": "string"
      +      },
      +      "message": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "error"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "message": {
      +        "type": "string"
      +      },
      +      "next_action": {
      +        "type": "string"
      +      },
      +      "operation_id": {
      +        "type": "string"
      +      },
      +      "status": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "operation_id",
      +      "status"
      +    ],
      +    "type": "object"
      +  }
      +]
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (destructiveHint=false, openWorldHint=true), and the description adds genuinely new context: it consumes AI usage, runs in LiveKit test rooms, and "Never dials a phone number, publishes settings or invokes connected external tools." That negative-scope statement is the most valuable line here. It stops short of saying whether the call blocks until the conversation completes or how to retrieve results (get_agent_test).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the core action, then the scenario rules, then the side-effect boundaries. No filler and no repetition of the title.

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?

An output schema exists, so return values need not be described, and the cost/side-effect picture is covered. But for an 8-parameter tool with a nested custom_scenario object and a uuid request_id, the definition omits idempotency-replay behavior, what number_id refers to, and how to follow up on a started test.

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 only 13%, so the description must carry weight, and it does explain the scenario/custom_scenario/scenario_description interplay and the inbound/outbound constraint. It says nothing about request_id (idempotency key), number_id, revision semantics, or responder_outcome beyond what the schema states, leaving half the surface undocumented.

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: "Run one isolated synthetic conversation against the active agent settings at the supplied revision." The single-run, isolated framing plus revision pinning distinguishes it from the lifecycle siblings (get_agent_test, stop_agent_test, get_agent_test_listener) without needing to name them.

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

Usage Guidelines3/5

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

Provides real conditional guidance for the direction parameter: "Outbound supports preset or custom fictional scenarios; inbound requires custom_scenario or scenario_description." However, it never says when to run a test versus generate_test_scenario or list_test_scenarios, and gives no prerequisites beyond the scenario rules, so usage is implied rather than fully specified.

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