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

Annotations already flag destructiveHint=true, but the description adds substantial context beyond them: no data is lost but access is, dependent apps will throw a database error, the password is not recoverable, a same-named user gets a new password, and — crucially — it discloses what is NOT verified (the database's fate) and forbids over-claiming. It also states the list-not-retrievable failure mode and that it does NOT mean the user is absent.

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 core action and the sibling contrast, then layered with operational caveats. It is long for a 2-param tool and a few clauses (e.g. "Sage es genau so, statt es zu behaupten") are meta-instruction rather than tool semantics, but nearly every sentence carries actionable content.

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?

Complete for a destructive mutation with no output schema: it covers prerequisites, downstream impact, irreversibility of credentials, an explicit uncertainty boundary, and failure-mode interpretation. Nothing an agent needs to call or accurately explain this tool 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% and the schema already documents both params, so the baseline is 3. The description adds real meaning about the `user` param's resolution: the login is validated server-side against the subscription's own database users, so a guessed or foreign value never reaches the hosting system. That is genuine semantics beyond the schema, though it does not add format details.

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 ("Löscht einen Datenbank-Benutzer") and immediately positions it relative to siblings: it is the reverse of create_database_user, and it explicitly is NOT a delete_database operation (the database presumably stays). An agent can distinguish it from both create_database_user and delete_database 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?

Explicitly instructs the agent to ask the customer beforehand whether anything still uses this user, and names the concrete place to check in WordPress (wp-config.php). It also names the counterpart tool (create_database_user) and distinguishes the operation from database deletion, so when-to-use and when-not-to-use are both covered.

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