Skip to main content
An agent that embeds its tools is limited by them. If execution tools are built into the agent — a hardcoded Bash tool, a built-in file reader, a baked-in HTTP client — then the agent’s tool surface is fixed at development time. It can only operate in environments that match those built-in tools. Change the environment, and the agent breaks or cannot adapt. This is a special-purpose agent: capable within its designed context, brittle outside of it. A general-purpose agent has no intrinsic tools beyond cognition. It does not embed tools that touch the environment. Instead, it declares its intended capabilities via a manifest and uses external MCP servers provided by the environment. The same cognitive core can operate as a coding assistant in one environment, a research agent in another, and a system administrator in a third — depending entirely on which MCP servers are available. This is the architectural consequence of the Cognitive Plane / Action Plane separation:

Embedded tools lock the agent to a fixed tool surface

The agent can only use the tools that were built into it. Giving it more tools requires modifying the agent itself.

Externalized tools via MCP make the tool surface composable

The agent can operate across environments where the Action Plane can support its declared intended capabilities. To give the agent more tools to work with, the environment adds or binds MCP servers — the agent doesn’t change.

Specialization comes from the agent loop, not from embedded tools

Two agents using identical MCP servers can behave entirely differently based on their system prompts, skills, reasoning architecture, and goals. The tools don’t define the agent — the cognition does.
This is what “general-purpose” means in GPARS. The standard does not make agents smarter or more capable. It makes them portable, composable, and environment-independent by ensuring they are not architecturally bound to a fixed tool surface. Every normative requirement in this specification — the plane separation, the manifest, the enforcement model, the security policy — exists to support and enforce this principle.