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, enabling distributed architectures and agent marketplaces without a shared tech stack.
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 at the expense of 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 achieved against the need to maintain 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 achieved at the expense of 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