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

Annotations already flag destructiveHint and idempotentHint, but the description goes well beyond them: it describes asynchronous background execution, the exact preservation rule (unsubscribes and blocks retained without the address, so it stays unmailable), irreversibility, and a required user confirmation step. That is precisely the operational context an agent needs before calling a destructive tool.

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 tight sentences: what it does and what is destroyed first, the preservation caveat second, the irreversibility warning and next step last. Nothing is redundant and the risk warning is not buried.

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?

Covers the destructive and asynchronous nature thoroughly for a two-parameter tool with no output schema, and it points to get_contact_erasure rather than describing return values. It stops short of saying what happens when erasure is already in flight for the same address or how long completion typically takes.

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 carry the parameter burden, and it only partially does: 'an address from a project' implies the pairing of email and project_id but gives no format, case-sensitivity, or failure behavior for an unknown address. Useful scoping signal, but not full compensation.

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 (erase) and a specific resource scope (a contact address within a project), and enumerates exactly what is removed: the contact, its enrollments, every send and its replies. This is clearly distinguishable from the sibling delete_contact, which would not carry the privacy-request semantics.

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 explicitly ('for a privacy request') and names the follow-up tool get_contact_erasure for polling. It does not explicitly say when to prefer delete_contact or block_email instead, so the exclusion versus siblings is implied rather than stated.

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