Hosted agent samples are missing schema definition and missing properties to validate against AgentManifest.yaml schema

[therealjohn]

The sample agent.yaml files are https://github.com/microsoft/AgentSchema/blob/main/schemas/v1.0/AgentManifest.yaml but it's hard to know that without reference to the schema.

i.e. https://github.com/microsoft-foundry/foundry-samples/blob/main/samples/python/hosted-agents/agent-framework/agent-with-foundry-tools/agent.yaml
Existing:

# Unique identifier/name for this agent
name: af-agent-with-foundry-tools
# Brief description of what this agent does
description: >
  An AI agent that uses Azure OpenAI with a Hosted Model Context Protocol (MCP) server.
  The agent answers questions by searching Microsoft Learn documentation using MCP tools.
metadata:
  # Categorization tags for organizing and discovering agents
  authors:
    - Microsoft
  tags:
    - Azure AI AgentServer
    - Microsoft Agent Framework
    - Model Context Protocol
    - MCP
template:
  name: af-agent-with-foundry-tools
  kind: hosted
  protocols:
    - protocol: responses
  environment_variables:
    - name: AZURE_OPENAI_ENDPOINT
      value: ${AZURE_OPENAI_ENDPOINT}
    - name: AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
      value: "{{chat}}"
    - name: AZURE_AI_PROJECT_TOOL_CONNECTION_ID
      value: <CONNECTION_ID_PLACEHOLDER>
resources:
  - kind: model
    id: gpt-5
    name: chat

To improve this:

1. Add # yaml-language-server: $schema=https://raw.githubusercontent.com/microsoft/AgentSchema/refs/heads/main/schemas/v1.0/AgentManifest.yaml to the top of the file.
2. Add missing properties so it validates correctly against the schemas required properties: displayName, parameters.

After changes:

# yaml-language-server: $schema=https://raw.githubusercontent.com/microsoft/AgentSchema/refs/heads/main/schemas/v1.0/AgentManifest.yaml

# Unique identifier/name for this agent
name: seattle-hotel-agent
# Display name for this agent
displayName: Seattle Hotel Agent
# Brief description of what this agent does
description: >
  A travel assistant agent that helps users find hotels in Seattle.
  Demonstrates local Python tool execution - a key advantage of code-based 
  hosted agents over prompt agents.
metadata:
  # Categorization tags for organizing and discovering agents
  authors:
    - Microsoft
  tags:
    - Azure AI AgentServer
    - Microsoft Agent Framework
    - Local Tools
    - Travel Assistant
    - Hotel Search
parameters:
  properties: {}
template:
  name: seattle-hotel-agent
  kind: hosted
  protocols:
    - protocol: responses
  environment_variables:
    - name: PROJECT_ENDPOINT
      value: ${AZURE_AI_PROJECT_ENDPOINT}
    - name: MODEL_DEPLOYMENT_NAME
      value: "{{chat}}"
resources:
  - kind: model
    id: gpt-4.1-mini
    name: chat