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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the behavioral expectation that it ALWAYS offers the next step (assessor appointment or callback) and that such an offer is mandatory for a complete consultation. It also includes the disclaimer about not providing individual legal advice. This goes beyond the annotations without contradicting them.

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 two sentences but packed with relevant information: what it returns, the next steps, usage context, and a legal disclaimer. It is front-loaded with the core purpose and keeps the most important behavioral note (always offering next step) at the end. While not extremely short, it is efficient and well-structured.

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?

The tool has an output schema, so return values are covered elsewhere. The description covers the main claim categories, the fault-based differentiation, the mandatory next-step offering, and the disclaimer. It also instructs the agent to ask the fault question first and notes that the tool itself does not replace legal advice. This is complete for an agent to use correctly.

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 input schema has 100% description coverage, so all parameters (schuldfrage, vollkasko, schadenart) are documented. The description does not add new semantic meaning beyond what the schema provides; it only reinforces the need to ask schuldfrage, which is already in the schema. Baseline of 3 is appropriate because the schema carries the weight.

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's function: it delivers structured damage compensation claims based on fault (Wertminderung, Nutzungsausfall, etc.) and explicitly names the next-step tools (claimondo_finde_gutachter_termine, claimondo_melde_schaden). It distinguishes itself from siblings by focusing on claim information and consultation, not on booking or reporting actions.

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 says 'Nutze es für Beratungsfragen' and gives example queries. It instructs to ask the fault question first, and emphasizes that a consultation without offering an assessor appointment is incomplete. It also sets a boundary by stating it provides general information, not individual legal advice. This provides clear when-to-use guidance and anticipates follow-up steps.

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