> ## Documentation Index
> Fetch the complete documentation index at: https://gpars.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Rationale

> Why GPARS makes the design choices it does.

<AccordionGroup>
  <Accordion title="Separation of Cognition and Action">
    Prevents cognitive bias induced by embedded execution tools. When tools are internal, the agent's reasoning is shaped by their implementation. Externalization ensures the agent reasons about *what* to do, not *how* tools work.
  </Accordion>

  <Accordion title="User-Owned Security">
    The user owns the data and systems the agent operates on. The user — not the agent, not the agent developer — defines what is permitted. This mirrors established security models in operating systems, cloud platforms, and enterprise infrastructure.
  </Accordion>

  <Accordion title="Declarative Agent Capabilities">
    Improves transparency and runtime portability without binding the agent to specific MCP server implementations. An agent's manifest describes its intended behavior using manifest-local capability references and human-readable descriptions.
  </Accordion>

  <Accordion title="Discovery-Based Authorization">
    Agents are not told their effective permissions. They discover boundaries by receiving denials. This prevents agents from gaming policy boundaries and keeps the security model simple.
  </Accordion>

  <Accordion title="Modularity">
    Enables emergent behavior across heterogeneous MCP capability ecosystems. Different cognitive models, reasoning architectures, and vendors can be composed without rewriting tool logic.
  </Accordion>

  <Accordion title="General-Purpose Validity">
    A truly general-purpose agent operates across environments without presuming intrinsic capabilities. Specialization comes from the agent loop — not from embedded tools.
  </Accordion>
</AccordionGroup>