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

Annotations only declare the generic profile (not read-only, not destructive, idempotent); the description adds the operationally decisive facts: a 14-day recovery window after which the call is refused and the data is unrecoverable, refusal on demo sites, and that the action is written to the privacy audit log. None of this is derivable from annotations or schema, and nothing contradicts them.

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?

Three sentences, front-loaded with the core action, then the time constraint, then the discovery pointer and side effects. Every clause carries new information; no repetition of the title or name.

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 mutation tool with annotations but no output schema, the description covers timing, refusal conditions and audit logging well. It stops short of stating what happens on the edge cases an agent may hit — an email that was never deleted, or an unknown email — and does not say what the response reports back, but nothing essential to invoking it correctly 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 coverage is 100% — email (exact-as-given), site_id (from list_sites) and optional user_goal are already documented in the schema. The description reinforces the single-email scoping ('for one email address') but adds no format, matching or ambiguity guidance beyond what the schema provides, so the 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+resource pair ('undo delete_privacy_data for one email address') and enumerates exactly what is restored: contact records, form submissions and contact activity. Explicitly anchored to the sibling it reverses, so an agent can distinguish it from delete_privacy_data, export_privacy_data and get_privacy_ops_status without opening a schema.

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?

Gives the trigger (undoing a delete), two hard refusal conditions (14-day window elapsed, demo sites), and names get_privacy_ops_status as the tool that lists who is still restorable. The when-not cases are stated outright rather than left to inference.

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