manual.texi Added an explanation to the end of FULLTEXT section

Docs/manual.texi

@@ -36507,6 +36507,18 @@ carefully tuned up this way). For very small tables, word distribution
 does not reflect adequately their semantical value, and this model
 may sometimes produce bizarre results.
 
+For example search for the word "search" will produce no results in the
+above example. Word "search" is present in more than half of rows, and
+as, such, is effectively treated as stopword (i.e. with semantical value
+zero). It is, really, the desired behaviour - natural language query
+should not return every second row in 1GB table.
+
+The word that select 50% of rows has low ability to locate relevant
+documents (and will find plenty of unrelevant documents also - we all
+know this happen too often when we are trying to find something in Internet
+with search engine), and, as such, has low semantical value in @strong{this
+particular dataset}.
+
 @page
 @cindex environment variables, list of
 @node Environment variables, Users, MySQL internals, Top