Skip to main content
Glama
EntraID MCP Server

EntraID MCP Server

by baoduy

Create Application

create_application

Create a new application (app registration).

Instructions

Create a new application (app registration).

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": {
      "app_data": "<app_data>"
    },
    "name": "create_application"
  }
}

Input Schema

NameRequiredDescriptionDefault
app_dataYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

C2.2/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so safety semantics are covered; the description adds nothing on top. It does not state what happens to an app with duplicate identifiers, whether the operation is idempotent or reversible, what permissions are needed, or what the response contains — all relevant for a creation tool taking an opaque payload.

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

Conciseness3/5

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

It is a single short sentence with the useful qualifier front-loaded, so there is no bloat — but brevity here comes from omission rather than efficiency. The one clause that earns its place is "(app registration)"; the rest merely echoes the title.

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?

An output schema exists, so return values need not be explained, but the input side is a free-form nested object with no documentation anywhere. For a write tool against an identity platform, the description should at minimum sketch the payload shape or point to list_applications/get_application_by_id for the schema of an app object.

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

Parameters1/5

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

There is a single required parameter, app_data, defined as an untyped object with additionalProperties=true and 0% schema description coverage. The description offers zero guidance on which keys are required or permitted (displayName, signInAudience, requiredResourceAccess, etc.), so the agent has no way to construct a valid call from either the schema or the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is essentially a restatement of the name/title ("Create a new application"), with one genuinely useful gloss: "(app registration)", which tells the agent this is an Azure AD app registration rather than a service principal or group. That plus the specific verb makes the resource identifiable, but nothing is said about what an application contains or how it differs from the sibling create_service_principal beyond the parenthetical.

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?

No when-to-use guidance, no prerequisites (e.g. permission scopes), and no routing to alternatives such as create_service_principal or create_group, all of which are plausible near-misses for an agent asked to "register an app". The agent must infer the choice entirely from the tool name.

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