diff --git a/spec/registry.md b/spec/registry.md
index b00a1aeab2..04f65ad876 100644
--- a/spec/registry.md
+++ b/spec/registry.md
@@ -422,6 +422,20 @@ The following options and their values are required to be available on the funct
 - `maximumSignificantDigits`
   - ([digit size option](#digit-size-options))
 
+If the _operand_ of the _expression_ is an implementation-defined type,
+such as the _resolved value_ of an _expression_ with a `:number` or `:integer` _annotation_,
+it can include option values.
+These are included in the resolved option values of the _expression_,
+with _options_ on the _expression_ taking priority over any option values of the _operand_.
+
+> For example, the _placeholder_ in this _message_:
+> ```
+> .input {$n :number notation=scientific minimumFractionDigits=2}
+> {{{$n :number minimumFractionDigits=1}}}
+> ```
+> would be formatted with the resolved options
+> `{ notation: 'scientific', minimumFractionDigits: '1' }`.
+
 > [!NOTE]
 > The following options and option values are being developed during the Technical Preview
 > period.
@@ -489,6 +503,14 @@ MUST be multiplied by 100 for the purposes of formatting.
 
 The _function_ `:number` performs selection as described in [Number Selection](#number-selection) below.
 
+#### Composition
+
+When an _operand_ or an _option_ value uses a _variable_ annotated,
+directly or indirectly, by a `:number` _annotation_,
+its _resolved value_ contains an implementation-defined numerical value
+of the _operand_ of the annotated _expression_,
+together with the resolved options' values.
+
 ### The `:integer` function
 
 The function `:integer` is a selector and formatter for matching or formatting numeric 
@@ -498,7 +520,6 @@ values as integers.
 
 The function `:integer` requires a [Number Operand](#number-operands) as its _operand_.
 
-
 #### Options
 
 Some options do not have default values defined in this specification.
@@ -538,6 +559,18 @@ function `:integer`:
 - `maximumSignificantDigits`
   - ([digit size option](#digit-size-options))
 
+If the _operand_ of the _expression_ is an implementation-defined type,
+such as the _resolved value_ of an _expression_ with a `:number` or `:integer` _annotation_,
+it can include option values.
+In general, these are included in the resolved option values of the _expression_,
+with _options_ on the _expression_ taking priority over any option values of the _operand_.
+Option values with the following names are however discarded if included in the _operand_:
+- `compactDisplay`
+- `notation`
+- `minimumFractionDigits`
+- `maximumFractionDigits`
+- `minimumSignificantDigits`
+
 > [!NOTE]
 > The following options and option values are being developed during the Technical Preview
 > period.
@@ -605,6 +638,14 @@ MUST be multiplied by 100 for the purposes of formatting.
 
 The _function_ `:integer` performs selection as described in [Number Selection](#number-selection) below.
 
+#### Composition
+
+When an _operand_ or an _option_ value uses a _variable_ annotated,
+directly or indirectly, by a `:integer` _annotation_,
+its _resolved value_ contains the implementation-defined integer value
+of the _operand_ of the annotated _expression_,
+together with the resolved options' values.
+
 ### Number Operands
 
 The _operand_ of a number function is either an implementation-defined type or