Future length limits need to define the text unit

[xfq]

https://webmachinelearning.github.io/webmcp/#mitigation-restrict-input-lengths

The mitigation section refers to limiting “characters”. For non-ASCII text, “character” is ambiguous: code points, code units, grapheme clusters, bytes, and model tokens differ. See https://w3c.github.io/bp-i18n-specdev/#characters

Please define limits in precise units, and avoid byte-based limits for user-facing text.

[beaufortfrancois]

https://webmachinelearning.github.io/webmcp/#tool-definition-name says

The name’s length must be between 1 and 128, inclusive, and only consist of ASCII alphanumeric code points, U+005F LOW LINE (_), U+002D HYPHEN-MINUS (-), and U+002E FULL STOP (.).