Skip to main content
Glama
TsvetanG2

cognigy-ai-mcp-management-server

by TsvetanG2
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
TypeScript

create_intent

Create a new intent in a Cognigy.AI flow for NLU recognition. Validate changes with dryRun first, then train the NLU model to enable matching.

Instructions

Creates a new intent in a Cognigy.AI flow for NLU recognition. MUTATING: This modifies the flow. Use dryRun=true (default) to validate first. After creating, use train_intents to train the NLU model.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesIntent name (unique within the flow)
tagsNoTags for organizing intents
rulesNoAdditional rule patterns for matching
dryRunNoIf true (default), validates without creating. Set to false to actually create.
flowIdYesThe flow ID where the intent will be created
localeIdNoLocale ID for the example sentences. Defaults to the locale the intent is created in.
conditionNoCognigyScript condition for additional matching constraints
isDisabledNoWhether the intent is disabled (won't match)
descriptionNoHuman-readable description of what this intent recognizes
exampleSentencesNoInitial training sentences for the intent (created as example sentences, same as create_sentence)
confirmationSentencesNoSentences used for intent confirmation

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.1
    • changedInput schema / properties / exampleSentences / description
      Previous value: -"Initial training sentences for the intent"New value: +"Initial training sentences for the intent (created as example sentences, same as create_sentence)"
    • addedInput schema / properties / localeId
      Added value: +{
+  "description": "Locale ID for the example sentences. Defaults to the locale the intent is created in.",
+  "type": "string"
+}
  2. First observedv0.1.4

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so 'MUTATING: This modifies the flow' largely restates them. However the description adds genuinely useful behavior not in the annotations: the dryRun-by-default safe-validation flow and the train_intents follow-up dependency, which materially change how an agent invokes it.

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 short sentences, zero waste, with the mutation/dryRun workflow front-loaded before the follow-up step. Every sentence earns its place.

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?

For an 11-parameter mutating tool with annotations but no output schema, the description covers purpose, mutation semantics, the dryRun safety path, and the next workflow step. It does not describe any return value or what a successful create yields, but that gap is minor given no output schema is declared.

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 100%, so all 11 parameters (including dryRun, localeId, condition) are already documented in the schema. The description's only parameter commentary is restating dryRun=true as the default. Baseline 3 is appropriate when the schema carries the semantic load.

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 (creates) plus resource (intent) and qualifies scope with 'in a Cognigy.AI flow for NLU recognition'. This distinguishes it from sibling mutators update_intent, delete_intent, and the downstream train_intents without needing to open 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 concrete workflow guidance: 'Use dryRun=true (default) to validate first' and 'After creating, use train_intents to train the NLU model', naming the follow-up sibling explicitly. It stops short of stating when NOT to use this tool (e.g. vs update_intent for existing intents), so it falls just under full marks.

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