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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial behavior: pagination via after=nextCursor with a 30-minute validity, sortAsOf pinning the occurrence clock across pages, result ordering rules, exclusion of open and unstructured legacy series, and explicit 'keine Buchung oder privaten Daten'. That is well beyond the safety hints.

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 but front-loaded: core purpose first, then filters, then result ordering, then pagination. Every clause carries distinct information, though the middle section reads as a long run-on cascade that could be broken up for scanability.

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 7-param tool with no output schema, the description explains result ordering, occurrence fields (matchedOccurrences, nextOccurrence), empty-result help fields (withoutRegionCount, alternativeRegions, hint), exclusions, and cursor semantics. Only the q and limit parameters and the 'no events, so search again within 30 minutes' boundary conditions are left underspecified.

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?

With 0% schema description coverage across 7 params, the description must carry the load and largely does: it defines region/category as catalog slugs, eventFrom/eventTo as inclusive YYYY-MM-DD in Europe/Zurich (explicitly not advertising runtimes), and after as the cursor with its TTL. It leaves q and limit unexplained, so the coverage is strong but not complete.

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 ('Sucht kostenlos nach öffentlich lesbaren Regiobrett-Einträgen') and enumerates exactly what is covered (Veranstaltungen, Kultur, Kurse, Vereine, lokale Angebote) plus the geographic scope (Ostschweiz). It also bounds the tool with 'keine vollständige Veranstaltungsübersicht', so an agent knows precisely what it will and won't return.

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 actionable routing: region/category are catalog slugs and 'zum Entdecken ohne Filter suchen' tells the agent when to search unfiltered, while the date-filter explanation shows which results each mode yields (dates vs range). No alternatives tool exists to name, but the description does not spell out when *not* to use keyword q versus region/category beyond the unfiltered tip.

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