analyze_terraform_plan and evaluate_terraform_policies both consume a local plan JSON file, which creates surface-level overlap, but the descriptions draw a clear line (summarize identities/actions vs. run OPA policy findings, with explicit 'performs no compliance evaluation' disclaimers). list_policies is unambiguously distinct as pure catalog discovery.

All three tools use a consistent snake_case verb_noun pattern (analyze_/evaluate_/list_) with the resource clearly stated. The noun varies appropriately with the target object (terraform_plan, terraform_policies, policies) rather than indicating inconsistency.

Three tools is on the thin side, but the server has a narrow, well-defined scope (read-only Terraform plan governance) and each tool maps to a distinct phase: discovery, structural summary, policy evaluation. No tool feels redundant or filler.

The core lifecycle for a read-only governance server is covered: list what policies exist, inspect what a plan will do, and evaluate it. Minor gaps remain — no tool to enumerate plan files in the allowed directories and no way to fetch full detail for a single policy — but agents can work around these by supplying paths and relying on list_policies output.