Trampoline Park Data Agent API

The three tools map to distinct retrieval phases: `about` for orientation/schema and document ids, `search` for natural-language passage retrieval, `fetch` for reading a known id. There is mild overlap since `about` also surfaces document ids and `search` can return sample content, but the descriptions make the intended sequence clear.

All three names are single lowercase verbs (`about`, `fetch`, `search`) following one uniform convention. The style is minimal but entirely predictable and consistent across the set.

Three tools is a tight, well-scoped set for a read-only data retrieval API, and each earns its place in the about→search→fetch flow. It sits at the low end of the typical range, with little room for a dedicated enumeration or filtering tool.

Discovery (`about`), query (`search`), and retrieval (`fetch`) cover the core lifecycle for public read-only data, so no dead ends for typical agent workflows. Minor gaps remain: no explicit way to enumerate or paginate all documents, and no structured field/filter queries beyond plain language.