Enterprise coding agents translate natural-language analytical requests into executable code using proprietary APIs, schemas, and metric definitions. However, the current deployment method of injecting exhaustive schema and tool documentation into every prompt increases inference overhead, complicates schema evolution, and undermines reliability in multi-turn analysis. We investigate whether stable schema knowledge and tool-use behavior can be acquired through post-training while preserving the consistency required for production-facing analytics.\n\nWe present CRAFT, a two-stage post-training recipe for schema-grounded coding agents. First, schema-stripped PLAN supervised fine-tuning learns domain-structured plans and executable behaviors from validated trajectories without exhaustive prompt-time schema injection. Second, execution-shaped reinforcement learning aligns the policy for tool selection, code quality, plan-code consistency, and recovery from failed executions. Training trajectories are curated through a Tri-Gate filter combining execution validation, data-integrity checks, and LLM-judge reasoning audit.\n\nWe evaluate CRAFT for planned rollout in advertising analytics, covering campaign performance analysis, metric drill-downs, entity-level performance analysis, and multi-turn analytical refinement. The enterprise evaluation environment incorporates beta APIs as the agent-facing tool surface and spans 25 schema-linked core entities and 30 agentic workflows. Relative to a schema-stuffed baseline, CRAFT improves composite Agent Score by +9.6 pp, consistency by +4.1 pp, and multi-turn coherence by +4.2 pp, while reducing input-token burden by approximately 9x and schema-discovery loops by up to 5x. We further report deployment tradeoffs, reward-shaping limitations, and training-infrastructure extensions required for multi-turn tool-use reinforcement learning in enterprise settings.\n\nBlogger's Review: CRAFT effectively addresses the pitfalls of traditional schema injection by leveraging post-training strategies, enhancing efficiency and consistency in multi-turn analysis. This not only optimizes resource utilization but also offers new insights for developing enterprise-level analytical tools, holding significant practical and research implications.