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

Annotations declare a non-read-only, non-destructive, open-world mutation; the description adds materially: the password is generated server-side (the agent must not ask for one), the default-directory resolution and its '/' fallback, the security consequence of an explicit '/', and the instruction to report only the directory actually returned. These are behavioral facts an agent cannot derive from the annotations.

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?

Purpose is front-loaded, followed by default behavior, then the safety warning, then the response-handling rule. Four sentences, each earning its place; only the parenthetical example '/httpdocs' is mildly redundant with the schema.

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?

With no output schema, the description compensates by explaining that the effective directory is only trustworthy from the response. Schema already covers parameters fully. Minor gaps remain: no statement about required permissions, login uniqueness, or what happens on invalid input.

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 the baseline is 3, but the description adds real meaning beyond it: it discloses that no password parameter exists because the server generates it, and it reinforces the default/explicit-'/' semantics of 'home' with a security rationale the schema only states mechanically.

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 einen zusätzlichen FTP-Zugang für eine Domain an.' The 'zusätzlichen' qualifier and the FTP/domain framing make it unmistakable among siblings (no other create_* tool targets FTP accounts; create_email_account and create_protected_directory are clearly different resources).

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 conditional guidance: omitting 'home' yields the domain's directory, and it flags the dangerous case of explicitly passing '/'. It also supplies a crucial downstream rule ('nur das darf dem Kunden genannt werden'). However, it never names an alternative tool or a when-not-to-use condition (e.g., use reset_ftp_password for existing accounts), so it stops short of full routing guidance.

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