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

Annotations already cover read-only, idempotent, and non-destructive properties, so the description doesn't need to repeat them. However, it adds valuable behavioral context by stating this tool is for polling (not push) and by describing conditional follow-up actions based on the unread count. This goes beyond the structured annotations and helps the agent understand the operational pattern.

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?

The description is three sentences, front-loaded with the core purpose, then adds usage guidance and follow-up actions. It is efficient with no fluff, though it could be slightly tightened. The structure is logical and easy to parse.

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 explicitly listing the return fields (with whom, entry, ownership, empty status, last message, unread). It also includes usage context and follow-up steps, making the tool self-contained for an agent. Minor omissions like error handling or pagination details are not critical for a simple list tool.

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?

The schema covers the parameter fully (name 'anzahl', type number, range 1-100, default 30, sort order 'neueste zuerst'). The description does not add meaning beyond that, so the baseline of 3 applies. It is adequate but not enhanced.

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 description clearly states the tool lists ongoing conversations ('Listet die laufenden Unterhaltungen') and enumerates specific fields returned (participant, associated entry, ownership flag, empty status, last message, unread counts). This is specific and distinguishes it from siblings like 'nachrichten_lesen' or 'nachricht_senden', which are follow-up actions rather than list operations.

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?

The description explicitly states when to use this tool: 'Kein Push — pollen, wenn der Nutzer fragt ob jemand geschrieben hat, oder periodisch.' It also provides a concrete post-call flow: 'Bei ungelesen_gesamt > 0: nachrichten_lesen, dann nachricht_senden mit chat_id.' This gives clear context and routing to related tools, leaving no ambiguity about when to invoke it.

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