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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds behavioral context: it specifies that periods apply from 2015 onward, notes the 2025 change (eight instead of ten years for vouchers), and cites legal bases (ArbZG, MiLoG). This goes beyond annotations by clarifying the data's scope and temporal limitations.

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 reasonably concise, front-loaded with 'Nur Deutschland', and lists the relevant categories. It includes a bilingual English translation which is slightly redundant but helpful for non-German speakers. It is structured and not overly long, with each sentence contributing content.

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?

There is no output schema, so the description should ideally explain what the tool returns. It describes the data (retention periods) but does not explicitly state the format (e.g., text, table) or whether it returns results for a specific date or all categories. It also doesn't mention edge cases or error conditions. Given the tool's simplicity, this is a minor gap, but it is still incomplete.

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% with descriptions for both datum and bestandteil. The tool description adds value by listing the document categories in German (Lohnkonto, Buchungsbelege, Bücher und Abschlüsse, Geschäftsbriefe, Arbeitszeitnachweise) which map directly to the enum options, and by stating 'ab 2015' which constrains the datum parameter. This enriches understanding beyond the schema.

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 provides retention periods for personnel and payroll documents in Germany, listing specific document types (Lohnkonto, Buchungsbelege, etc.) and the time frame (since 2015). It also includes an English summary. This is specific and distinct from sibling HR tools which cover other topics like taxes, leave, or thresholds.

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 gives clear context: it is for Germany and covers retention periods. It does not explicitly name alternatives or say when not to use it, but the scope is so specific that an agent can infer when to choose it. The constraint 'Nur Deutschland' and the listing of covered categories provide sufficient guidance without explicit exclusions.

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