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/decisions.md

@@ -118,7 +118,7 @@ that extension's `evidenceRef` slot.
 clock. FIDES stacks on `trust-annotations` because a scheme has no meaning
 without the slot it fills.
 
-## 2026-06-17 — Schemes carry data labels; host architectures do not
+## 2026-06-16 — Schemes carry data labels; host architectures do not
 
 **Decision.** `schemes/` holds **data-labelling** approaches a server attaches to
 a result (FIDES, Permissive IFC, AirGapAgent, `data-class`, attestation
@@ -131,7 +131,7 @@ one. Conflating them would invite a `schemes/camel.md` that has no per-result
 payload to define. A capability token such an architecture issues can still be
 *referenced* through `evidenceRef`, but the architecture itself is not a scheme.
 
-## 2026-06-17 — Early SEP-1913 feedback recorded as cited open questions
+## 2026-06-16 — Early SEP-1913 feedback recorded as cited open questions
 
 **Decision.** The substantive concerns from the original issue (#711) and SEP
 (#1913) review — the set-theoretic critique of linear sensitivity, org-defined
@@ -145,3 +145,22 @@ lot of debated design. Recording *why*, with links to the people who raised each
 point, keeps the history visible and gives each parked item a home to graduate
 from (a scheme, an `action-metadata` field, or a future extension) instead of
 being re-litigated from scratch.
+
+## 2026-06-16 — `sensitive` is a lowest-common-denominator floor; emit both
+
+**Decision.** The coarse `sensitive` boolean is intentionally a
+lowest-common-denominator signal — a universal, always-actionable floor that
+supports a basic "better than nothing" egress/consent policy even against a
+barely-known server. It is the basic, general scheme every participant
+understands, **not** a competitor to richer schemes. Servers SHOULD emit **both**
+the boolean and a richer `evidenceRef` scheme (e.g. `data-class.v1`,
+`ifc.fides.v1`) where they can; `sensitive` MUST NOT be dropped merely because a
+scheme is present.
+
+**Rationale.** Clarifies the original purpose of the boolean (raised by Sam): the
+point of keeping it on the wire was never to *replace* richer classification but
+to guarantee a floor any client can act on. Richer schemes are strictly more
+capable but are not universally implemented, so they cannot be the floor —
+layering the two gives universal actionability without capping what advanced
+hosts can do. This also answers the "boolean vs. richer taxonomy" tension from
+SEP-1913 review: it is not either/or, it is both, at different layers.

docs/open-questions.md

@@ -10,27 +10,30 @@ Tracked here rather than in the spec drafts, so the drafts stay non-temporal.
 - **Cross-domain integrity verification** — is asymmetric crypto for domain
   identity in scope for a future extension, or out of scope entirely? CLI tools
   remain a persistent gap for enforcing these constraints.
-- **`evidenceRef.type` registry** — who curates the list of well-known profile
+- **`evidenceRef.type` registry** — who curates the list of well-known scheme
   types, and how do we coordinate with attestation SEPs (e.g. SEP-2787) so
   values don't collide?
 
 ## trust-annotations
 
-- **Shape of the sensitivity signal.** Is `sensitive: boolean` the right single
-  coarse signal, or does the narrow cut overcorrect? The SEP-1913 thread rejected
-  a linear `sensitiveHint: low|medium|high` because sensitivity is set-theoretic,
-  not a scale ([@JustinCappos](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/711#issuecomment-2967516811):
-  medical results to a mail MCP *and* a card number to a payment MCP, but neither
-  crossed). Reviewers then pushed for org-defined vocabularies
+- **Sensitivity beyond the floor.** The `sensitive` boolean is settled as the
+  **lowest-common-denominator floor** — a basic, general signal every client can
+  act on, "better than nothing," with servers encouraged to *also* emit a richer
+  scheme (see the [decision log](./decisions.md) and the "emit both" guidance in
+  the spec). The residual open question is narrower: is "coarse boolean + richer
+  `evidenceRef` scheme" sufficient for regulated flows, or do some hosts need the
+  classification expressible *on the wire* without a scheme? Current lean: **no
+  wire escape hatch** — keep the wire floor un-rottable and push the taxonomy
+  into [`data-class.v1`](../schemes/data-class.md). Background on why a single
+  scalar/enum was rejected: sensitivity is set-theoretic not linear
+  ([@JustinCappos](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/711#issuecomment-2967516811)),
+  reviewers wanted org-defined vocabularies
   ([@olaservo](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/711#issuecomment-2968743154),
   [@Mossaka](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/711#issuecomment-2971788308))
-  and a class+regulatory pairing such as `confidential:hipaa`
-  ([@krubenok](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/1913#discussion_r3103485194)).
-  Against that, [@localden](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/1913#issuecomment-4037623595)
-  warned a baked-in taxonomy is hard to remove. Open: keep the boolean and let
-  the [`data-class.v1` scheme](../schemes/data-class.md) carry the taxonomy, or
-  also expose a structured escape hatch on the wire so regulated flows are
-  expressible without a scheme?
+  and a class+regulatory pairing
+  ([@krubenok](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/1913#discussion_r3103485194)),
+  and a baked-in taxonomy is hard to remove
+  ([@localden](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/1913#issuecomment-4037623595)).
 - **Enforcement vs. advisory.** A self-declared `sensitive: true` from a
   poorly-configured or malicious server could create a false sense of security
   ([@localden](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/1913#issuecomment-4037623595)).

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
 

specification/draft/trust-annotations.mdx

@@ -40,7 +40,10 @@ broadly-applicable signals cover the majority of client-actionable cases:
   Drives prompt-injection defenses.
 
 Anything richer than these two booleans is deliberately **not** on the wire; it
-hangs off `evidenceRef` (see below).
+hangs off `evidenceRef` (see below). These two signals are a
+**lowest-common-denominator floor**, not a ceiling: servers are encouraged to
+*also* attach a richer scheme via `evidenceRef` — see
+[Coarse vs. rich](#coarse-vs-rich-classification-dataclass).
 
 ## Specification
 
@@ -113,7 +116,7 @@ SEP-1913 carried a four-level data classification
 (`public` / `personal` / `confidential` / `highly_confidential`) plus a
 regulatory scope (e.g. `confidential:hipaa`). **This extension deliberately
 keeps only the coarse `sensitive` boolean on the wire.** Richer classification
-is recovered as an `evidenceRef` profile:
+is recovered as an `evidenceRef` scheme:
 
 ```jsonc
 "evidenceRef": {
@@ -124,9 +127,19 @@ is recovered as an `evidenceRef` profile:
 }
 ```
 
-This is an explicit scope decision: the binary lives on the wire for universal
-client actionability; the taxonomy lives behind a profile so it can evolve
-without a breaking schema change.
+This is an explicit scope decision. The boolean is the **lowest-common-
+denominator signal**: a universal, always-actionable floor that lets any client
+apply a basic egress/consent policy that is *better than nothing*, even against a
+server it knows little about. It can be thought of as the basic, general scheme
+that every participant understands. Richer schemes are strictly more capable but
+are not universally implemented, so they cannot be the floor.
+
+Servers SHOULD therefore emit **both** when they can: the coarse `sensitive`
+boolean for universal actionability, **and** a richer `evidenceRef` scheme (e.g.
+`data-class.v1`, `ifc.fides.v1`) for hosts that implement it. The two are
+layered, not alternatives — a client that understands the scheme uses it; one
+that does not still has the boolean. `sensitive` MUST NOT be omitted merely
+because a richer scheme is present.
 
 ### Attachment point
 
@@ -189,8 +202,11 @@ and `evidenceRef` is how that claim is made checkable.
 
 ## Open questions
 
-- Is `sensitive` the right single coarse signal, or do we need `sensitive` +
-  the `data-class.v1` profile from day one?
+- `sensitive` is settled as the lowest-common-denominator floor; servers are
+  encouraged to emit it **and** a richer scheme. Residual: is the
+  [`data-class.v1` scheme](../../schemes/data-class.md) enough, or do some
+  regulated flows need the classification *on the wire*? See
+  [docs/open-questions.md](../../docs/open-questions.md).
 - Exact required-vs-recommended split on `evidenceRef` fields.
 - Whether content-block-level annotation needs a worked multi-result example
   before the draft is implementable.
@@ -201,3 +217,4 @@ and `evidenceRef` is how that claim is made checkable.
 | ---------- | ------------------------------------------------------------- |
 | 2026-06-10 | Initial draft skeleton. Narrowed to `sensitive` + `untrusted` + `evidenceRef`; DataClass demoted to a profile; `requires_review` moved to `action-metadata`. |
 | 2026-06-16 | Show `jcs/rfc8785` alongside `cbor/rfc8949` so canonicalization reads as a per-reference envelope choice, not a default; note the `type`/`digest`/`canonicalization` triple as the local-re-derivation minimum. (Review: @Rul1an.) |
+| 2026-06-16 | Add `untrusted` vs `openWorldHint` relationship subsection; frame `sensitive` as the lowest-common-denominator floor and recommend servers emit both the boolean and a richer `evidenceRef` scheme. |