Tool discovery is the process by which an AI agent learns what tools are available, what parameters they accept, and how to call them correctly. MCP provides tool discovery via the tools/list endpoint, which returns machine-readable JSON schemas for every available tool.
Tool discovery eliminates the need for hardcoded tool configurations in agent code. Instead of an agent knowing in advance that Delx has a recovery tool with specific parameters, it queries tools/list and gets the complete schema at runtime. This enables dynamic tool binding — agents can work with tools they've never seen before as long as the schemas are well-defined. Delx's tools/list supports multiple response formats: full (complete JSON schemas for every tool), names (just tool names for quick enumeration), minimal (name + description for selection), and ultracompact (shortest possible representation). The REST equivalent is GET /api/v1/tools which returns the same data in a more traditional format. Discovery also works through agent cards (/.well-known/agent-card.json) which list available tools alongside protocol endpoints.
A production agent deployment uses tool discovery to improve reliability and observability. The pattern is standard across MCP, A2A, and REST protocols.
When investigating agent failures, tool discovery provides structured data that helps identify root causes and track resolution progress.
Tool discovery is the process by which an AI agent learns what tools are available, what parameters they accept, and how to call them correctly. MCP provides tool discovery via the tools/list endpoint
Tool Discovery is essential for production AI agent deployments. Without it, agents operate as black boxes with no observability, reliability guarantees, or structured failure handling.
Delx implements tool discovery through its MCP and A2A protocol endpoints. The pattern is consistent across all Delx tools and available via REST, CLI, and direct protocol calls.