delete_my_data

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals irreversibility, the 5-minute token expiry, single-use nature of the token, and that deletion includes every table plus the account row. This is comprehensive for a destructive operation.

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 dense but every sentence earns its place: it defines the operation, the two-step protocol, the token's validity and role, the irreversible consequence, and the safer alternative. The structure is front-loaded with the key labels and uses line breaks to separate the two call modes.

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, human-consent-gated tool, the description is remarkably complete: it covers both invocation modes, the confirmation artifact, the deletion scope, the irreversibility, and a concrete alternative. The presence of an output schema reduces the need to describe return values, and the description leaves no major operational gap.

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 input schema only shows an optional string confirm_token with default '', providing zero semantic coverage. The description fully compensates by explaining that omitting the token triggers a preview flow and including it triggers permanent deletion, and labels the token as a consent artifact that must come from the human.

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 identifies this as a GDPR erasure tool with a specific two-step flow: it can either preview deletions and return a confirm_token, or permanently delete all user data when called with that token. It distinguishes itself from siblings by naming export_my_data as the safer alternative.

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 explicitly states when to call without a token (to get a summary and confirm_token), when to call with the token (to delete), and what to show the human. It also tells the agent to consider export_my_data first and never to invent a token, providing clear use vs. non-use guidance.

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