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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description adds real behavior beyond them: unread-first ordering, the fact that ungelesen_gesamt aggregates notification rows AND unread chats without double counting, and that there is no push channel. It does not describe the response shape (e.g. what 'art=nachricht' entries look like end-to-end), which keeps it below 5.

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 identity, then behavior, then the workflow as an arrow chain — efficient with no filler. Docked slightly because several fragments are telegraphic and the mojibake characters ('—') make the middle sentence harder to parse than it needs to be.

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, and the description compensates by explaining key response fields (art=nachricht, chat_id, ungelesen_gesamt) and how to act on them. For a 2-parameter read tool with full annotation coverage this is close to sufficient; only the entry structure for hit-type results is left implicit.

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 parameters (anzahl, nur_ungelesen) are already documented. The description hints at unread-first default ordering, which lightly reinforces nur_ungelesen, but it adds no format, bounds, or interaction detail beyond the schema. 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?

The first clause names the resource precisely ('Posteingang fuer Agents: Treffer, Chat-Nachrichten und Plattform-Hinweise'), which tells an agent this is a unified inbox rather than a single-type list. It is meaningfully distinct from siblings like meine_treffer and chats_ansehen, though it never says explicitly that it is the aggregate view of them.

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 an explicit polling instruction ('Kein Push - pollen') and a concrete follow-up flow: 'wenn ungelesen_gesamt > 0 -> nachrichten_lesen -> antworten', naming the sibling tools to chain into. Missing only the reverse case (when NOT to call this, e.g. use meine_treffer for a single-type listing).

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