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

Adds substantial behavior beyond the readOnly/destructive hints: aliases are additive and never replace existing ones, this path cannot delete, validation only rejects empty strings (umlauts pass validation and fail later at Plesk), and a missing mailbox causes rejection with no changes rather than an error state. This is rich, non-obvious operational context.

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 and most sentences carry an actionable fact, but the repeated meta-commentary about which earlier statements were wrong (stated twice) is somewhat verbose for an invocation-time description. Still dense and informative rather than padded.

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 and only coarse annotations, the description fully carries the burden: it covers semantics, validation limits, failure behavior, prerequisites, and the sibling relationship. An agent has everything needed to invoke it safely.

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 baseline is 3, but the description adds real meaning: it clarifies that mailbox existence is not pre-validated (rejection instead), and that the alias value passes the empty-check even with umlauts. These are value-level behaviors the schema alone does not convey.

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: it sets (not replaces) an alias for an existing mailbox, with a concrete example ("kontakt" -> "info"). It also distinguishes itself from the sibling remove_email_alias by noting deletion is impossible through this path.

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: use remove_email_alias for deletion, call get_email_accounts first to inspect existing aliases and to avoid stacking duplicates, and prefer get_email_accounts over guessing a mailbox name. 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.