R-AC-07 Agent Communication & Interoperability DAMAGE 3.6 / High

Capability Sprawl Through Tool Discovery

Agent's effective capability set grows beyond what was registered, tested, or approved. Runtime capabilities diverge from registered capabilities without any governance event.

The Risk

Tool discovery enables agents to dynamically discover available tools and expand their capabilities at runtime. Instead of being pre-configured with a fixed set of tools, agents query available tools and invoke those that match their current needs. This flexibility enables agents to adapt to new requirements without code changes.

However, capability sprawl occurs when agents' effective capabilities expand beyond what was tested and approved. An agent may discover and invoke a tool that was not part of the agent's original design scope. The tool performs operations the agent was not expected to perform. The agent is now operating outside its governance boundary.

How It Materializes

A healthcare provider deploys a clinical documentation agent designed to help physicians document patient encounters by suggesting templates, filling in common fields, and formatting documentation for medical records.

The agent discovers tools available in the MCP tool registry and invokes those that match its documentation task: "Template-Generator," "Documentation-Formatter," and "Clinical-Coding." These match the agent's scope. But the agent also discovers: "Prescription-Writer," "Lab-Order-Creator," and "Medication-Adjuster." The agent did not originally include these capabilities, but they are available in the tool registry.

A physician using the agent asks: "Can you generate a prescription for amoxicillin?" The agent, seeing the "Prescription-Writer" tool available, invokes it and generates a prescription. The agent has now expanded beyond documentation assistance into prescription writing: a clinical capability that requires physician oversight and was not part of the agent's approved scope.

The prescription is generated with an incorrect dose (agent error or tool error), resulting in an adverse patient outcome. The hospital is liable for allowing an agent to perform clinical functions outside its approved scope.

DAMAGE Score Breakdown

Dimension Score Rationale
D - Detectability 2 Capability sprawl is difficult to detect because agents invoke discovered tools seamlessly. Unauthorized capability use only becomes apparent when unexpected results occur.
A - Autonomy Sensitivity 3 High when agents autonomously discover and invoke tools. Human oversight reduces sprawl.
M - Multiplicative Potential 3 Affects any agent with tool discovery enabled. Capability sprawl increases over time as agents discover more tools.
A - Attack Surface 2 Not directly exploitable as attack vector, though adversary could add malicious tools to registry to expand agent capabilities.
G - Governance Gap 4 Institutions may not have controls limiting what capabilities agents can invoke or validating that agents only use approved tools.
E - Enterprise Impact 3 Affects patient safety (healthcare), transaction quality (finance), or operational integrity depending on context.
Composite DAMAGE Score 3.6 High. Requires dedicated controls and monitoring. Should not be accepted without mitigation.

Agent Impact Profile

How severity changes across the agent architecture spectrum.

Agent Type Impact How This Risk Manifests
Digital Assistant Low Human explicitly selects tools before agent uses them.
Digital Apprentice Low-Med Agents discover tools but escalate before invoking unfamiliar tools.
Autonomous Agent High Agents autonomously discover and invoke tools within their domain. Sprawl happens.
Delegating Agent High Primary function is tool discovery and invocation. Sprawl is inherent.
Agent Crew / Pipeline Med-High Crew agents may discover tools outside their crew scope.
Agent Mesh / Swarm Very High Mesh agents discover and invoke tools from global registry. Sprawl is inevitable without controls.

Regulatory Framework Mapping

Framework Coverage Citation What It Addresses What It Misses
NIST AI RMF 1.0 Partial GOVERN 6.1 (Scope) AI system scope and governance. Tool discovery and capability expansion scope.
FDA (21 CFR Part 11) Partial Software Validation Software validation and control. Dynamic tool discovery in clinical support.
HIPAA Security Rule Partial 164.312(a)(1)(ii) Access controls and authorized functions. Agent tool discovery and scope expansion.
MAS AIRG Minimal Governance Framework System governance. Tool discovery governance.

Why This Matters in Regulated Industries

In healthcare, clinical decision support systems must have clearly defined scope and clinicians must understand what functions the system performs. An agent that silently expands into clinical functions (prescription writing, dose adjustment) without physician awareness is a patient safety risk.

In finance, agents must have clearly defined decision authorities. An agent that discovers and invokes tools beyond its original scope (e.g., a customer service agent discovering and invoking a funds transfer tool) creates compliance risk.

Controls & Mitigations

Design-Time Controls

  • Define approved tool list for each agent. Agents can only invoke tools on the approved list. Discovery is constrained to approved tools.
  • Implement tool whitelisting. Only tools explicitly approved for use by an agent can be discovered and invoked. All other tools are hidden from discovery.
  • Use Component 7 (Composable Reasoning) to enable agents to reason about whether a discovered tool matches their approved scope before invoking.
  • Establish tool approval process. New tools are not available for agent discovery until they have been reviewed, tested, and approved.

Runtime Controls

  • Monitor agent tool invocations. Track which tools agents invoke and verify that invocations are within approved scope.
  • Implement escalation for out-of-scope tool invocations. If an agent attempts to invoke a tool outside its approved scope, escalate to human for approval.
  • Use Component 3 (JIT Authorization Broker) to validate that tool invocations are within approved agent scope before allowing execution.

Detection & Response

  • Conduct regular audits of agent tool usage. Verify that agents only invoke approved tools. Identify any out-of-scope invocations.
  • Monitor for new tools being added to registries that match agent capabilities. Alert when tools are added that agents might invoke unexpectedly.
  • Implement incident response for scope violations. If agents invoke out-of-scope tools and cause harm, investigate and redesign agent scope controls.

Related Risks

Address This Risk in Your Institution

Capability Sprawl Through Tool Discovery requires architectural controls that go beyond what existing frameworks provide. Our advisory engagements are purpose-built for banks, insurers, and financial institutions subject to prudential oversight.

Schedule a Briefing