Operational category
Tools
What the agent can touch.
Tool Registry
A catalog, not a kitchen sink.
Available tools are centrally registered alongside their schemas, descriptions, permissions, and metadata.
Trade-off Better tool governance is achieved against higher maintenance effort.
MCP
Tools speak a shared protocol.
External resources and tools are made available via the Model Context Protocol as a standardized integration layer.
Trade-off Broad interoperability is gained at the cost of additional operational and permission management overhead.
A2A Protocol
Agents address other agents.
Open standard for interoperable agent-to-agent communication across system and network boundaries. Remote agents can be invoked as tools, inside graphs, or within swarms as if they were local.
Trade-off Vendor independence and isolation are gained against early-stage tooling and additional protocol overhead.
Function Calling
Structured JSON in, typed function call out.
The model emits a structured call — a named function with typed, schema-validated arguments — that the harness executes, feeding the result back into the model's context; the model decides which function to call, when, and with what arguments.
Trade-off Structured control is gained against schema definition and integration effort.
Adapter Pattern
Wrap the messy API in a clean tool the model can call.
A wrapper translates a messy or unstable external API into a small, stable, agent-friendly tool contract — so the model sees one clean function while the adapter absorbs auth, pagination, error handling, and schema drift behind it.
Trade-off More stable agent interfaces are gained against the cost of maintaining an additional code layer.
Capability Routing
Pick the tool by what it can do, not what it's called.
A request is matched to the tool, agent, or service whose declared capability fits it — selection by capability metadata rather than a hardcoded condition — and a missing capability is detected explicitly instead of silently mis-routed.
Trade-off Flexible selection is gained against the risk of misallocation and policy complexity.
Permission-scoped Tools
Each tool carries the smallest permission set that lets it work.
Each tool is provisioned with the minimal permissions its use requires, scoped per agent, task, or run — so the credential a tool call carries, not merely which tools exist, bounds what a compromised or misdirected call can reach.
Trade-off Enhanced security is gained against higher administration overhead.
Agentic RAG
Retrieve only when it helps — and decide that yourself.
The agent decides autonomously whether, when, and how to retrieve — issuing and reformulating queries, selecting among sources, grading the relevance of returned passages, and iterating or skipping retrieval — instead of unconditionally retrieving once before generation. Named variants: Self-RAG (reflection tokens gate retrieval), Corrective RAG / CRAG (an evaluator scores evidence and triggers re-retrieval or a web fallback), GraphRAG (a knowledge graph for multi-hop questions), and RAPTOR (hierarchical tree-structured retrieval for long material).
Trade-off Higher relevance and recall are bought with extra LLM calls, added latency, and a larger failure surface (mis-decided retrieval, query-reformulation loops).
Where to next