fix comments

Author: samchon

packages/interface/src/schema/ILlmFunction.ts

@@ -1,3 +1,4 @@
+import { tags } from "..";
 import { IJsonParseResult } from "./IJsonParseResult";
 import { ILlmSchema } from "./ILlmSchema";
 import { IValidation } from "./IValidation";
@@ -21,11 +22,11 @@ export interface ILlmFunction {
    * Function name for LLM invocation.
    *
    * The identifier used by the LLM to call this function. Must be unique within
-   * the application. OpenAI limits function names to 64 characters.
+   * the application.
    *
-   * @maxLength 64
+   * OpenAI limits function names to 64 characters.
    */
-  name: string;
+  name: string & tags.MaxLength<64>;
 
   /**
    * Schema for function parameters.
@@ -90,9 +91,8 @@ export interface ILlmFunction {
    * Type validation is NOT performed — use {@link validate} after parsing.
    *
    * If the SDK (e.g., LangChain, Vercel AI, MCP) already parses JSON internally
-   * and provides a pre-parsed object, use `LlmJson.coerce()` from
-   * `@typia/utils` instead to apply schema-based type coercion without
-   * re-parsing.
+   * and provides a pre-parsed object, use {@link coerce} instead to apply
+   * schema-based type coercion without re-parsing.
    *
    * @param str Raw JSON string from LLM output
    * @returns Parse result with data on success, or partial data with errors
@@ -104,8 +104,8 @@ export interface ILlmFunction {
    *
    * **Use this only when the SDK (e.g., LangChain, Vercel AI, MCP) already
    * parses JSON internally.** For raw JSON strings from LLM output, use
-   * {@link parse} instead — it handles both lenient parsing and type coercion
-   * in one step.
+   * {@link parse} instead — it handles both lenient parsing and type coercion in
+   * one step.
    *
    * LLMs often return values with incorrect types even after parsing:
    *
@@ -132,10 +132,10 @@ export interface ILlmFunction {
    * numbers or missing required properties. Use this validator to check
    * arguments before execution.
    *
-   * When validation fails, use `stringifyValidationFailure()` from
-   * `@typia/utils` to format the error for LLM feedback. The formatted output
-   * shows the invalid JSON with inline error comments, helping the LLM
-   * understand and correct its mistakes in the next turn.
+   * When validation fails, use {@link LlmJson.stringify} from `@typia/utils` to
+   * format the error for LLM feedback. The formatted output shows the invalid
+   * JSON with inline error comments, helping the LLM understand and correct its
+   * mistakes in the next turn.
    *
    * @param args The arguments generated by the LLM
    * @returns Validation result with success status and any errors