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

Annotations only declare it is a non-read-only, non-destructive, open-world write. The description adds what those hints cannot: the password is generated server-side and displayed exactly once (an irrecoverable side effect), and a duplicate-address rejection leaves the existing mailbox untouched and is explicitly not an error. That is precisely the behavior an agent must know before calling.

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-loads the action, then immediately surfaces the two highest-risk facts (one-time password, duplicate rejection is normal), and closes by routing to the inspection sibling. No filler sentences.

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?

There is no output schema, so the description must – and does – explain the key return value: the generated password delivered once in the response. Combined with the failure-mode explanation, an agent has everything needed to call and interpret this tool.

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 100%: both 'domain' and 'local_part' are documented with format rules and valid/rejected examples, so the schema already carries the parameter semantics. The description adds no parameter-level information, making the baseline 3 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 ('Legt ein neues E-Mail-Postfach auf einer Domain an') and names the sibling that inspects state instead ('get_email_accounts zeigt den Bestand'), making it distinguishable from delete_email_account and get_email_accounts at a glance.

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 clear operational context: no pre-check of existence, the failure mode if the address is taken, and where to look at existing mailboxes. It does not explicitly contrast with alternatives like set_email_alias or setup_email_provider, so 4 rather than 5.

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