Scored across 7 tools
Each tool has a clearly distinct role, and the descriptions explicitly cross-reference alternatives (e.g. search_web vs fetch_page vs verify_claims vs get_citations). The only potential overlaps — KB search vs web search, provider inspection vs config reload — are sharply bounded by stored-vs-fresh and read-only-vs-mutating semantics.
All tools use the same infobroker_ prefix followed by a consistent snake_case verb_noun pattern: get_citations, fetch_page, inspect_providers, manage_kb, reload_config, search_web, verify_claims. There is no mixing of casing or verb styles.
Seven tools is well within the appropriate range for a research/information-broker server. Each tool earns its place by covering a distinct workflow stage: discovery, retrieval, citation, verification, storage, diagnostics, and configuration.
The surface covers the core research lifecycle: search, page fetch, citation generation, claim verification, knowledge-base storage/recall, provider inspection, and config reload. Minor gaps exist, such as no explicit update/edit action for existing KB entries beyond ingest, but agents can work around this.