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

Goes well beyond the destructiveHint annotation: it discloses that the old password becomes invalid, that active mail clients must be reconfigured, that a non-existent mailbox is rejected with the previous password still valid, and that this rejection is not an error. This is exactly the operational 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?

Four front-loaded sentences: action, side effect, edge case, remedy. Each sentence carries distinct operational value with no filler; the warning about active mail clients is deliberately emphasized.

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?

No output schema exists, yet the description covers purpose, side effects, failure behavior, and prerequisite lookup. For a two-parameter destructive tool this leaves nothing an agent would need 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 description coverage is 100%, so both domain and local_part (including the character rules and examples) are already fully documented in the schema. The description adds only the procedural hint not to guess the name, so baseline 3 applies.

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 ('Setzt das Passwort eines bestehenden E-Mail-Postfachs zurück'), which cleanly distinguishes it from siblings reset_ftp_password and reset_wordpress_admin_password. An agent can identify the target object without opening the 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?

Explicitly routes the agent to a sibling ('Im Zweifel vorher get_email_accounts aufrufen, statt den Namen zu raten') and defines the boundary condition of a missing mailbox. The when-to-use and precondition are both stated rather than inferred.

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