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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing result shapes (url/ecli/cited_by for decisions, slug/ref_norm for statutes) and the handoff protocol into getNorm and the decision tools. It also flags a genuine quirk (Hessen rows need law_key/ref_norm) and corpus coverage limits via getCoverage. It stops short of describing result volume, ranking behavior beyond the sort enum, or empty-result behavior.

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 citation-absence rule, then chained output/interop details, then filters, then an example — a sensible order. It is dense and parenthetical-heavy (semicolon-joined clauses about Hessen and field names), but almost every clause carries operational information an agent needs.

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?

For a 12-parameter discovery tool with no output schema, it covers the essentials: what comes back, how to route those fields into downstream tools, which corpora are covered, and how to constrain results. Remaining gaps (pagination behavior past limit, cases_total semantics, what happens on zero hits) are minor but real for a tool this broad.

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?

At 50% schema coverage the description does real work: it explains that q accepts German keywords or a full question and that decisions are matched semantically, enumerates which filters apply to decisions (court, court_level, state, panel, from/to, decision_type), and glosses the sort values as "relevance, weight: most cited first, newest." It adds little for limit (default 10, max 50, undescribed in both places) and leaves `sort`'s "weight" only partially 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?

Opens with a specific verb and resource plus the scope of the corpus: "Find statutes and decisions on a topic or a question, in one call." It also pre-empts confusion with the citation-driven siblings by stating "Use it when you hold no citation yet," so the agent can classify it against resolveIdentifiers/getNorm without reading schemas.

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?

States a clear entry condition ("when you hold no citation yet") and repeats narrowing policy in the schema text ("Narrow only when you know which corpus answers"). What it never does is name the alternative tool to use when a citation IS held, leaving the agent to infer resolveIdentifiers as the counterpart.

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