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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes further: it enumerates exactly what is destroyed (record, name, fields, proof of consent, tags), what is preserved (campaign statistics, suppression list), and flags IRREVERSIBLE with the consent precondition. This is precisely the extra context annotations cannot carry.

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 dense sentences, front-loaded with the erasure scope, then the preserved-data boundaries, then the alternative and the irreversibility warning. Every clause carries actionable information.

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 single-parameter destructive tool with no output schema, the description covers scope, side effects, preconditions, and the routing alternative. An agent has everything needed to call it correctly and safely.

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 0% and there is one required parameter (email), which the description never describes. The parameter name is self-evident, so no real ambiguity results, but the description adds no semantics such as exact-match requirements or behavior when the email is not found.

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 (erases) and resource (a person from the workspace) and frames it as a GDPR right-to-erasure operation, which separates it cleanly from generic subscriber deletion. It also explicitly names the sibling it is not (remove_subscriber).

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 an explicit when-to-use condition ('only use it on the explicit request of the person concerned, relayed by the user'), an explicit when-not ('To stop someone receiving anything, use remove_subscriber — not this one'), and names the alternative. Nothing is left to inference.

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