No user-submitted related servers found.
Scored across 17 tools
The discovery cluster (list_sections / describe_section / inspect_sections) and the lookup cluster (get_entity / find_entities / list_entities) overlap conceptually, but the descriptions explicitly state when to prefer each and cross-reference alternatives. The JSONata family (query_dataset / seaf_jsonata_query / describe_query_result / find_jsonata_examples) is likewise differentiated by scope (dataset vs manifest vs result-shape vs examples). A few boundaries remain soft, but an agent can pick correctly.
Most tools follow a clean verb_noun snake_case pattern (list_sections, get_entity, find_entities, describe_query_result). However, two tools are auto-derived raw endpoint names (get_seaf_core_api_core_storage_versions, get_seaf_core_api_core_storage_problems) that break the convention badly, and seaf_jsonata_query adds an inconsistent domain prefix.
17 tools is on the heavier side but each maps to a distinct step in the discovery→inspect→query workflow, so they mostly earn their place. It could be trimmed (e.g. merging versions/problems into a diagnostics tool), but it is not bloated for the domain.
The surface covers health, section/structure discovery, entity lookup and relation traversal, metamodel guidance, JSONata examples, dataset access, query execution and result introspection — a full read-oriented lifecycle. Gaps are minor: no explicit dataset enumeration, and no write operations if mutation is in scope, but the read/query workflow has no dead ends.