Frame 'sensitive' as the lowest-common-denominator floor; recommend emitting both

Per Sam: the coarse 'sensitive' boolean exists to give a universal, 'better than
nothing' policy-enforcement floor every client can act on — a basic/general
scheme — not a competitor to richer schemes. It is not either/or with the
taxonomy; servers are encouraged to do both.

- trust-annotations.mdx: reframe the coarse-vs-rich section around the LCD floor;
  add a SHOULD-emit-both recommendation (boolean + richer evidenceRef scheme);
  point Motivation at it; reframe the in-spec open question accordingly;
  changelog row.
- decisions.md: log the LCD-floor + emit-both decision; correct two entries
  mis-dated 2026-06-17 to today (2026-06-16).
- open-questions.md: reframe the sensitivity item from 'is the boolean right' to
  the narrower residual (is boolean + data-class scheme enough, or is a wire
  escape hatch needed); current lean: no escape hatch.
- terminology: profile -> scheme in forward-looking text (open-questions
  registry line, sep-disposition SEP-2787 row); historical log entries left as-is.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

docs/sep-disposition.md

@@ -105,7 +105,7 @@ with it if it lands, but do not block on it.
 | 1862 | Tool Resolution (pre-flight) | Stays core / Standards Track | — (composes, no dependency) |
 | 1984 | Comprehensive Tool Annotations | IG discussion item | — |
 | 2417 | Model Preferences for Tools | IG discussion item | — |
-| 2787 | Tool Call Attestation | Candidate `evidenceRef` profile | (future) |
+| 2787 | Tool Call Attestation | Candidate `evidenceRef` scheme | (future) |
 
 ## Intent comment