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

Annotations declare destructiveHint=true, and the description goes well beyond them: it states messages to the alias will be rejected afterward while the mailbox and its messages are untouched, that mailbox AND alias are validated server-side against this subscription's mailboxes before removal, and the critical quirk that the hosting system reports success even when the alias never existed — so the server re-checks and returns an ERROR instead. It also explains the failure mode when the mailbox list is unavailable. This is exactly the behavioral context an agent needs.

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?

Front-loaded with the most important consequence (alias stops receiving mail) and the imperative to warn the customer. It is long, but nearly every sentence carries distinct operational value (reversibility path, validation behavior, false-success quirk). Slightly verbose, but justified.

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 3-param mutation tool with no output schema, the description covers consequences, reversibility, prerequisites, validation behavior, and even the false-success edge case. Nothing an agent needs to invoke this 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%, so all three params are documented in the schema themselves (including local-part vs. full-address formats and the alias-must-belong-to-this-mailbox constraint). The description adds value by pointing to get_email_accounts as the source of valid values and reiterating 'rate keinen', which supplements rather than contradicts the schema.

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 precise verb+resource and scope: 'Entfernt EINE Alias-Adresse von einem Postfach' — removes exactly one alias from a mailbox. Explicitly distinguishes itself from the sibling set_email_alias ('der Weg zurück') and from get_email_accounts, so the agent can differentiate 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 explicit when-to-use and consequential context: warn the customer beforehand that messages will be rejected, ask whether the address still appears anywhere (website, signature, business cards, forms), and routing guidance to use get_email_accounts rather than guessing the alias. Names both the alternative (set_email_alias) and the discovery tool.

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