Texas Code

Several tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and discover_tools all serve as broad data-query entry points, and the Polymarket suite (polymarket_arbitrage, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread, bet_research) blurs boundaries despite detailed descriptions. An agent could easily misselect, especially given the near-identical ask_pipeworx variants.

All tool names use snake_case, but the structural pattern is inconsistent: some are verb-first (ask_pipeworx, compare_entities, generate_llms_txt, validate_claim), some are noun-first (company_facts, entity_profile, polymarket_arbitrage, release_calendar_markets), and a few are bare verbs (forget, recall, remember). This is readable but lacks the cohesive verb_noun pattern expected of a well-designed set.

With 37 tools, the server is far too heavy for its apparent purpose. Even if the actual scope is broad data/prediction-market access, the count exceeds the 25-tool threshold that typically signals over-expansion. For a server named 'Texas Code' with only two law-related tools, the bloat is even more glaring.

The server name suggests Texas Code coverage, but only two tools (tx_codes, tx_statute) address that domain, and they provide no case law, court opinions, or search beyond statutory text. Meanwhile the majority of tools cover unrelated domains (Polymarket arbitrage, federal filings, weather), leaving the named purpose severely underserved. The broader data surface is fairly complete, but for the stated 'Texas Code' focus it is critically incomplete.