data_classification

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real value by enumerating what the output contains (regulation hints, handling controls, open questions) and flagging the legal-advice limitation, which is behavioral context an agent would otherwise have to infer.

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?

Two sentences, front-loaded with the action and outputs, and the legal-advice caveat earns its place as a risk boundary. No filler.

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?

The output schema covers return values and annotations cover safety, so the description mainly owes parameter guidance — which it omits entirely for a tool with three required parameters and a nested object array. Adequate on intent, incomplete on how to supply inputs.

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 0%, yet the description says nothing about `system`, `elements` (a nested structure requiring name/category/purpose/sharedWith), or `jurisdictions` (BR/EU/US/other). The regulation names hint at jurisdictions but never map them to the parameter or its codes, leaving the heaviest parameters undocumented.

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?

States a specific verb (classify) plus the resources and outputs (regulation hints for LGPD/GDPR/PCI DSS/HIPAA, handling controls, open questions). It is clearly distinct from advisory siblings like threat_model or well_architected_review, but it doesn't explicitly name what it is not.

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?

Usage is implied (run it against a system's data elements with target jurisdictions), and 'Review aid, not legal advice' sets expectations about its authority. However, there is no explicit when-to-use/when-not guidance and no named alternative among the many review-oriented siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.