Skip to main content
Glama
Dynamics 365 MCP Server

Dynamics 365 MCP Server

by Kenny-666

create_model_column

Destructive

Create native Dataverse columns—String, Memo, Integer, Decimal, Money, DateTime, Boolean, or Choice—with validation and a default preview before saving.

Instructions

Create native String, Memo, Integer, Decimal, Money, DateTime, Boolean, Picklist or MultiSelectPicklist column. Choice columns use local options or a validated global choice binding. Checks parent managed properties, publisher prefix and duplicate logical name. Default preview; save and publication remain separate.

Input Schema

NameRequiredDescriptionDefault
typeNo
dryRunNoDefault true performs reads/eligibility checks and returns a native request preview. Set false to execute.
formatNo
dry_runNoDefault true performs reads/eligibility checks and returns a native request preview. Set false to execute.
optionsNo
maxValueNo
minValueNo
maxLengthNo
max_valueNo
min_valueNo
precisionNo
trueLabelNo
falseLabelNo
max_lengthNo
schemaNameNo
true_labelNo
descriptionNo
displayNameNo
false_labelNo
logicalNameNo
schema_nameNo
defaultValueNo
display_nameNo
logical_nameNo
default_valueNo
requiredLevelNo
required_levelNo
dateTimeBehaviorNo
globalChoiceNameNo
date_time_behaviorNo
global_choice_nameNo
solutionUniqueNameNoExisting unmanaged solution; its publisher prefix is validated for new schemas.
environment_profileNoOptional named environment profile for this call; omit to use the configured default.
solution_unique_nameNoExisting unmanaged solution; its publisher prefix is validated for new schemas.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.2
    • addedInput schema / properties / environment_profile
      Added value: +{
      +  "description": "Optional named environment profile for this call; omit to use the configured default.",
      +  "pattern": "^[A-Za-z][A-Za-z0-9_]{0,31}$",
      +  "type": "string"
      +}
  2. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the pre-flight checks (parent managed properties, publisher prefix, duplicate logical name) and the dry-run default that returns a native request preview. Combined with destructiveHint=true, an agent knows the mutation is gated behind an explicit opt-in and that publishing is a separate step. It does not describe what happens on validation failure or what the preview contains.

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?

Four tight sentences with the resource and type list front-loaded, followed by the choice rule, validation checks, and the preview/publish split. Every sentence carries distinct information; there is no filler.

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 complex 34-parameter creation tool with no output schema and no annotation coverage of validation semantics, the description covers high-level behavior but omits critical parameter relationships (which options belong to which type, what the required logical/schema/display/solution fields mean) and the return shape of the preview. An agent still needs to inspect the schema heavily before calling it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 15% across 34 parameters, so the description must compensate and largely does not. It adds meaning for the type enum, the local-options vs global-choice binding, and publisher-prefix validation via the solution parameter, but leaves format, dateTimeBehavior, requiredLevel, precision, min/max, default values, and localized labels 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?

The description opens with a specific verb and resource ('Create ... column') and enumerates the nine supported column types, which immediately separates it from siblings like update_model_column_settings or create_model_choices. It also names the two choice mechanisms, making the boundary with create_model_choices clear.

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?

It gives real workflow guidance: preview is the default, and save plus publication are explicitly separate operations, which steers the agent away from assuming this tool publishes. It stops short of naming alternatives such as update_model_column_settings or publish_model_table, so it is clear context without explicit exclusions.

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