CFPB consumer complaints

Most tools have clearly distinct purposes, but a few boundaries blur: complaint_counts with group_by=year/quarter/month overlaps heavily with trend, and company_profile/compare_companies/complaint_counts(group_by=company) all slice company-level aggregates. The descriptions do a good job of steering usage (compare for up to 6 side-by-side, profile for one deep-dive), so misselection is unlikely but not impossible.

All names are snake_case, which is consistent, and the majority follow a verb_noun pattern (find_company, get_complaint, list_values, search_narratives, count_narratives, compare_companies). However, four tools break the pattern with noun-first names (company_profile, complaint_counts, dataset_info, trend), a minor but noticeable deviation.

Ten tools is well-scoped for a read-only public complaint-data API. Each tool earns its place: discovery (find_company, list_values, dataset_info), retrieval (get_complaint), and analytics (counts, trend, narratives, profile, compare) without obvious redundancy.

For a read-only analytical domain, the surface is essentially complete: company discovery, field enumeration, dataset metadata, single-record retrieval, structured aggregation, narrative search/count, and time trends are all present. No write operations are expected for public CFPB data, so no meaningful gaps remain.