record_breach

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

With no annotations provided, the description must disclose behavioral traits. It does so by explaining the 72-hour clock from aware_ts, the validation requirement that 'refers_to' ledger seqs must exist, and the significance of high_risk in deciding subject notification. It also implies partial data acceptance via 'as far as known'. These are meaningful disclosures that go beyond a simple 'records a breach', though it does not cover permissions, reversibility, or exact side effects.

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, dense sentence that is front-loaded with the core purpose and then systematically explains the clock, content, high_risk, and refers_to. It is concise relative to the complexity (12 parameters) and structured logically, with no wasted words.

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?

Given 12 parameters, no output schema, and no annotations, the description provides substantial context: the GDPR framework, the meaning of high_risk, the validation of refers_to, and the acceptance of partial data. It does not explain the 'title' and 'actor' fields, nor explicitly state the overall side effects of recording (e.g., creating a ledger entry), but for a complex tool it covers most essential aspects and would allow an agent to call it correctly.

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?

The schema has 0% description coverage, so the description must compensate. It explains several parameters: aware_ts (clock start), high_risk (Art. 34(1) judgement), refers_to (validated ledger seqs), and lists the content fields (nature, categories, numbers, contact, consequences, measures). It does not explicitly describe 'title' or 'actor', which are required, but covers the majority of fields with useful context, adding significant value beyond the bare schema.

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 the action ('Record a personal data breach') and references a specific regulatory context (GDPR Art. 33). It distinguishes this from sibling tools like record_incident or record_risk by focusing on data breaches specifically, and mentions the 72-hour clock and Art. 33(3) content, leaving no doubt about the tool's purpose.

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 clearly defines when this tool is appropriate (recording a GDPR data breach) and provides contextual detail such as the 72-hour clock and the role of high_risk. It does not explicitly name alternative tools or exclusions, but the specificity of the purpose makes it clear that general incidents, risks, or other actions belong elsewhere. This is strong context without explicit alternatives.

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