Skip to main content
Glama

conduyt_create_call_flow

Create a draft call flow with a named graph of entry, greeting, agent, menu, timing, and routing nodes, then validate and publish it to make it live on a phone number.

Instructions

Create a call flow. Starts as a DRAFT — edit the graph, validate, then publish to make it live on its number.

Input Schema

NameRequiredDescriptionDefault
nameYesFlow name
draftGraphNoInitial flow graph — MUST have a string entryId and a nodes array (anything else is silently replaced by a default voicemail flow server-side). Node kinds: entry, greeting, agent, group (queue: holdSeconds/pressOneVoicemail/repeatRing = queue mode), menu (options[{digit,label,next}], next = no-choice path), timing (hours[{day,start,end}], timezone, next = during hours, closedNext = outside hours), function (functionId = a registered function endpoint id, timeoutSeconds 2-8, next = success, failNext = failure; the JSON response's top-level scalars become call attributes), set_attributes (assignments[{key,value}] — value may use {{contact.firstName}} / {{call.from}} / {{attributes.x}}), branch (attribute, op equals|not_equals|contains|exists|not_exists, value, next = match, elseNext = otherwise), voicemail, forward, hangup. Spoken text in greeting/menu/voicemail/hangup may use {{contact.firstName|there}}, {{call.from}}, {{attributes.key}} (publish refuses unknown references). Every branch must reach an ending — publish refuses otherwise.
phoneNumberNoE.164 number this flow answers (must belong to the account)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.71.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and the key non-obvious behavior — the object is created in a non-live DRAFT state — is disclosed. However, it omits what the call returns (a flow id needed for subsequent edit/publish calls), any permission or phone-number ownership requirements, and there is no output schema to fill that gap.

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?

Two short, front-loaded sentences with no filler. The state transition, which is the most important thing an agent must know, comes before the follow-up workflow.

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 a deeply nested graph payload and no annotations or output schema, the description covers the lifecycle but not the outcome. An agent still lacks the created resource identifier and any permission preconditions needed to chain into validate/publish.

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% and the draftGraph property already documents node kinds, templating, and publish validation rules exhaustively. The description adds no parameter-level detail beyond the schema, so the baseline of 3 is correct.

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 call flow'), so an agent knows exactly what is produced. It does not distinguish itself from siblings like conduyt_update_call_flow or conduyt_create_call_flow_function, but the creation verb plus the draft lifecycle makes the scope unambiguous.

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 clear lifecycle context: the result is a DRAFT that must be edited, validated, then published. That tells the agent which follow-up calls are expected and that this tool alone does not make the flow live. It stops short of naming the sibling tools (validate/publish) or stating when to prefer updating an existing flow.

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