Detect compliance drift across 6 enterprise dimensions: NIS2 (CyberShield), ISO 27001 (CyberShield), LkSG (SupplyChainOracle), Contract DORA Art.28 (LegalTechOracle), DAC6 Tax (TaxOracle), Healthcare MDR (HealthGuard). Auto-logs drift events.
| Name | Required | Description | Default |
|---|---|---|---|
| entity_id | No | ||
| categories | No | Comma-separated: nis2, iso27001, lksg, contracts, tax, healthcare. Omit for all. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses 'Auto-logs drift events' as a side effect, but omits details about permissions, reversibility, or return behavior. This is a limited disclosure of behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that is front-loaded with the primary action. The long list of dimensions is necessary and directly relevant, making the description efficient without verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without an output schema or annotations, the description omits return value details, the meaning of entity_id, and the consequences of auto-logging. It provides the core purpose but leaves significant gaps, especially for the unspecified entity_id and operational details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% with entity_id undocumented. The description aligns with the categories parameter by naming the six dimensions, but does not help clarify entity_id or its usage. It adds some semantic value for categories but fails to compensate for the other parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Detect compliance drift across 6 enterprise dimensions' and enumerates the specific frameworks, which gives a specific verb+resource+scope. It distinguishes itself from sibling tools like detect_cloud_drift or detect_regulatory_drift by naming the exact enterprise dimensions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for detecting drift in the listed compliance frameworks, but does not explicitly state when to use it versus alternatives or when not to use it. No mention of sibling tools or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, with detection tools differentiated by drift type. Minor overlap exists between health_check and ping, as well as control_drift and evidence_drift sharing degraded controls, but descriptions provide enough context to avoid confusion.
The naming pattern is mixed: detect_* tools consistently use verb_noun, but drift_history and drift_status follow noun_noun, and full_drift_scan is a compound noun. While readable, the inconsistency makes the set feel less cohesive.
15 tools is slightly above average but justified by the broad scope of drift detection and management. Each tool earns its place, covering detection, viewing, configuration, and remediation without obvious redundancy.
The tool set covers the full drift lifecycle: detection (multiple types), full scan, history, status, configuration, manual marking/resolving, and automated remediation. Minor gaps like lacking a single-event detail view are not critical for core workflows.