diff --git a/docs/DEPLOY.md b/docs/DEPLOY.md
index fa2383b..eab3ed8 100644
--- a/docs/DEPLOY.md
+++ b/docs/DEPLOY.md
@@ -249,8 +249,9 @@ sudo docker compose -f docker-compose.server.yml exec backend python -m app.sync
 
 - `first-reply-facts`:跨日精确首响事实表(本地实测 11,020 会话 → 6.8 万行)。
 - `employee-metrics`:员工指标宽表 + 通话日小表(本地实测 12,371 宽表行 +
-  1,163 通话行);**必须在 first-reply-facts 之后跑**——宽表串类列
-  (threads_answered/首响分位)与 fact 表同源,先跑宽表会整体为 0。
+  1,163 通话行);**必须在 first-reply-facts 之后跑**——fact 表是后续评分/
+  下钻的数据源,须先填充(宽表自身从 message 表经同一算法重算串类列,
+  不读 fact 表,先跑宽表不会出 0,但 fact 缺失会阻塞后续能力)。
 - 两命令均为按日 delete+insert 幂等重建,复跑结果一致,中断重跑无副作用。
 
 ## 8. 本地收尾(部署验证通过后)
diff --git a/yunke-server/app/db/models.py b/yunke-server/app/db/models.py
index 7849632..2de19a0 100644
--- a/yunke-server/app/db/models.py
+++ b/yunke-server/app/db/models.py
@@ -1090,7 +1090,8 @@ class EmployeeMetricDaily(Base):
     reactivated_customer_count: Mapped[int] = mapped_column(
         Integer, nullable=False, default=0, server_default=sa.text("0")
     )
-    # fact 是否已覆盖当日(宽表生成前置条件;False=串类列可能滞后)
+    # 预留完整性标记:宽表生成当前恒写 True(串类列与 fact 同一算法直算,
+    # 不读 fact 表)——真实语义(如校验 fact 覆盖/同步完整)由批次B定义
     data_complete: Mapped[bool] = mapped_column(
         Boolean, nullable=False, default=False, server_default=sa.text("0")
     )
@@ -1102,8 +1103,9 @@ class EmployeeMetricDaily(Base):
 class EmployeeCallDaily(Base):
     """员工×日通话小表(v2 §1.2 #9)——通话无消息渠道维度,独立于宽表。
 
-    phone_call.channel 是通话类型(phone_call/voice_call)非消息渠道,
-    塞进 (day,channel,user) 宽表会在 channel=all 聚合时双计。接通 =
+    phone_call.channel 是通话类型(实测值 voice_call/wa_voice_call,
+    无蜂窝 phone_call 行)非消息渠道,塞进 (day,channel,user) 宽表会在
+    channel=all 聚合时双计。接通 =
     call_duration > 0;followup = 通话后 24h 内该员工任一账号对该客户
     有消息(Task 0 已核实:1:1 通话可匹配率 100%,@chatroom 群通话除外)。
     """
diff --git a/yunke-server/app/sync/cli.py b/yunke-server/app/sync/cli.py
index ba5086a..7aa0df4 100644
--- a/yunke-server/app/sync/cli.py
+++ b/yunke-server/app/sync/cli.py
@@ -157,8 +157,10 @@ def _build_parser() -> argparse.ArgumentParser:
         description=(
             "Full rebuild of the management wide table (per-day x channel "
             "x staff, 1:1 caliber) and the call daily table. Must run "
-            "AFTER first-reply-facts (thread columns share the same "
-            "source). Deploy backfill + nightly self-heal. Idempotent."
+            "AFTER first-reply-facts (the fact table feeds Batch-B "
+            "scoring and drilldown; both recompute threads from messages "
+            "via one shared algorithm). Deploy backfill + nightly "
+            "self-heal. Idempotent."
         ),
     )