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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description does add real behavioral value by disclosing the response shape, the ordering rule ('ausdrückliche Nennungen zuerst'), and the caveat that candidate_prefilter_truncated means the list is incomplete for heavily cited norms. However it never explains pagination or whether a truncated list can be completed, and no output schema exists to carry that burden.

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 purpose and the two query directions, then the result fields in a compact semicolon list. Dense and largely waste-free, though the field enumeration ('total_found, references, via_bereich') makes the middle section read as a spec dump rather than prose.

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 correctly compensates by naming the return fields and explaining via_bereich ('aus §§ 568 bis 576') and the truncation flag. It is complete for a lookup tool; the remaining gap is result-volume handling, since limit defaults to 20 and no paging behavior is described.

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 the schema already documents every parameter including limit, richtung, rechtsraum and same_law_only; the baseline of 3 applies. The description restates the richtung modes and the paragraph sub-level filter ('573 Abs. 2 Nr. 2'), but adds essentially nothing the schema does not already say.

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?

Names a specific resource (Querverweise) and makes the two modes unmistakable with concrete examples ('wer zitiert § 823 BGB?' vs 'worauf verweist § 242 BGB?'). It never names a sibling tool (e.g. normen or suche), so the agent must infer that this is a reference-graph lookup rather than norm-text retrieval; clear purpose, but no explicit sibling differentiation.

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 eingangs/ausgehend distinction with concrete example queries tells the agent when to pick each mode, and the truncated-result warning signals when the output should be treated as partial. It stops short of saying what alternate tool to use for plain norm text or for free-text search across the sibling set.

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