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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds substantial context they don't carry: soft delete with a 14-day hidden window, permanent purge by retention cleanup, audit-log recording, refusal conditions, and return contents. This is exactly the extra detail annotations cannot express.

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 destructive action and its scope come first, followed by reversibility, refusals and returns. Dense but nearly every clause carries operational weight; the audit-log note is the only marginal one.

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?

With no output schema, the description still tells the agent what is returned (counts per record type and the purge date). Combined with the reversibility window and refusal rules, nothing material is missing for correct invocation.

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 coverage is 100%, so email, site_id and user_goal are documented in the schema. The description reinforces the single-email scope but adds no format or edge-case detail beyond the schema. Baseline 3 is appropriate.

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 and resource plus exact scope: 'every contact record, form submission and contact-activity entry for one email address on this site.' That scoping distinguishes it from delete_submissions and export_privacy_data in the sibling list.

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?

Frames the use case (answer a deletion request) and names the companion restore_privacy_data for reversing it, plus the conditions under which it is refused (demo sites, privacy settings off). It stops short of explicitly contrasting with delete_submissions, but the scope sentence does the routing implicitly.

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