retention

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

With no annotations, the description carries the full burden and does so thoroughly: it flags read-only unless apply=True, admits hard-deletion, states that each erasure leaves a signed tombstone when applicable, and warns that omitting basis/request_id degrades auditability.

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 main behavior is front-loaded and the additional paragraphs earn their place by explaining destructive side effects, audit trail behavior, and why basis/request_id are important. It is dense but not redundant; a little trimming of the historical rationale would make it tighter.

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?

For a destructive tool with no output schema and no annotations, the description is strong: it names the return object, the side effect, and the audit implications. It could define 'ACTIVE' more precisely and state any limits/error behavior, but nothing essential to a first safe call is missing.

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%, so the description must explain the parameters; it covers max_age_days, apply, pii_only, basis, and request_id. It gives the purpose of each and explains why basis/request_id matter, though it does not specify expected value formats.

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 states the operation with a specific verb and resource: find ACTIVE records older than max_age_days and, with apply=True, hard-delete them. It also frames this as storage-limitation enforcement (GDPR Art. 5(1)(e)), distinguishing it from reporting tools like erasure_report or per-record forget tools.

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?

It gives clear operational guidance: dry-run by default, review {eligible, ids, applied, erased} before enforcing, and pii_only defaults to restricting to PII-tagged records. It does not explicitly name sibling alternatives or exclusion conditions, but the when/how context is clear.

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