AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

microsoft-foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Original source
microsoft
License
MIT
Pinned revision
3f5b461b2314e01c400564051e92469114c5b68f

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read microsoft--microsoft-foundry at revision 3f5b461b2314e01c400564051e92469114c5b68f, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 151

foundry-agent/create/references/tools/managed-harness-agent/agent-tools.md

Managed Harness Agent Tools

A Managed Harness Agent prefers tools declared directly in the Agent service's tools[]. Use a Toolbox only when explicitly requested.

| Capability | Authoring | Connection | |---|---|---| | Copilot built-ins | microsoft_copilot_toolset_preview for new authoring | No | | Web Search | web_search | No | | Code Interpreter | code_interpreter | No | | File Search | file_search | Existing vector store | | MCP server | mcp | Optional, depends on authentication | | Azure AI Search | azure_ai_search | Existing Cognitive Search connection | | OpenAPI | openapi | Conditional, depends on authentication | | Agent-to-Agent | a2a_preview | Optional | | Work IQ | Connection-authenticated mcp | Existing Work IQ connection | | Fabric IQ | fabric_iq_preview | Existing Fabric IQ connection | | Toolbox | Authenticated mcp to an exact version endpoint | Matching Toolbox connection |

Read the specific reference before editing:

Standard tool entries use Foundry REST field names, normally snake_case. Except for the Copilot toolset, azd validates little beyond a non-empty type; Foundry validates nested fields.

Legacy github_copilot_toolset_preview entries remain supported and must be preserved when editing an existing definition.

Do not add unsupported tools by guessing their schema. Do not create a connection or Toolbox unless the user explicitly requests creation.