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, and the description still adds real behavioral detail: ranked results, the response shape (results, snippet with bolded hit, zitat, absatz) and the zero-hit path. It does not discuss limit/offset paging semantics or cost, so it stops short of full transparency.

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?

Dense and front-loaded: purpose first, then syntax, then routing to `normen`, then the fallback workflow, then return shape. Nearly every clause carries actionable content, though the telegraphic style and count of semicolon-separated rules makes it slightly harder to parse than a clean two-or-three sentence definition.

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 7 optional parameters, no output schema and no required fields, the description covers what the agent must supply (query shape, category vs law list), what happens on failure, and what comes back. Nothing needed to invoke it correctly is missing.

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%, so baseline is 3, but the description genuinely adds a query mini-language (space = AND, OR, -term, "Phrase", prefix matching for composita) that is nowhere in the schema. It also explains the queries-array rationale and the laws-vs-kategorie split, though paging via offset stays purely schema-defined.

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?

States a specific verb (Stichwortsuche) on a specific resource (im amtlichen Wortlaut aller Normen im Bestand) and names the ranking (beste Treffer zuerst). It also explicitly differentiates from the sibling `normen` for the known-number case. An agent can pick between them without opening a schema.

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 both routing rules and query strategy: use `normen` when the paragraph number is known, use Fachbegriffe rather than whole questions, and on zero hits run typo correction then an OR search. This is explicit when-to/when-not guidance tied to concrete siblings and fallbacks.

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