docs: address final model experience review

packages/ui/acp-agent/README.md

@@ -48,11 +48,7 @@ All diagnostics go to **stderr** — stdout is the protocol.
 
 ## Model Experience
 
-### Composed ACP agent request
-
-**What the model sees**: Through `dsh-agent-core`, an ACP-created agent receives the harness identity, configured persona, skill catalog, visible tools, and its own ACP prompt history. This app adds no extra prompt prose and omits `ask_user_question` unless a leaf opts in.
-
-**Token effect**: Per-request cost is the sum of the composed child packages. ACP framing, JSON-RPC, persistence, and UI rendering add zero model tokens.
+Indirectly, through `dsh-agent-core` and `dsh-acp`, which compose each ACP agent's prompt, tools, and message history; this app bundle adds no model-bound content itself.
 
 ## Known Limitations and Deferred Work
 

packages/ui/stdio-agent/README.md

@@ -70,7 +70,7 @@ Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo —
 
 ### Composed terminal agent request
 
-**What the model sees**: Through `dsh-agent-core`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the `ask_user_question` schema. Each readline submission becomes a user message.
+**What the model sees**: Through `dsh-agent-core`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each readline submission becomes a user message.
 
 **Token effect**: Child prompt and schema costs repeat per request; user input and tool history grow until compaction. The welcome banner, logger output, and rendered transcript are terminal-only and add zero model tokens.
 

packages/ui/tool-ask-user/README.md

@@ -23,7 +23,7 @@ This is the consumer package for the user-interaction seam. It does not render U
 
 ### Tool schema
 
-**What the model sees**: The model sees `ask_user_question` with question ids, prompts, headings, options, and multi-select flags.
+**What the model sees**: The model sees the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user), including question ids, prompts, headings, options, and multi-select flags.
 
 **Token effect**: Fixed schema cost on every request where the tool is visible.
 

packages/ui/user-approval/README.md

@@ -16,10 +16,23 @@ Answerers today: the ACP bridge ([`@deepseek-ai/dsh-acp`](../../ui/acp/)) forwar
 
 ### System prompt and policy notice
 
-**What the model sees**: Under `ask`, every agent request carries exactly `<!-- dsh-user-approval-policy:ask -->`. Under `never`, it carries exactly ``Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).`` followed by a newline and `<!-- dsh-user-approval-policy:never -->`. A policy switch injects exactly `The approval policy changed from "<old>" to "<new>" (changed by the user).` or `The approval policy changed from "<old>" to "<new>" (changed by the operator/config).` before the next step.
+**What the model sees**: Under `ask`, every agent request carries the ask-policy prompt section below. Under `never`, it carries the never-policy prompt section below. A policy switch injects exactly `The approval policy changed from "<old>" to "<new>" (changed by the user).` or `The approval policy changed from "<old>" to "<new>" (changed by the operator/config).` before the next step.
 
 **Token effect**: Small fixed per-request cost, larger under `never`; a change notice is conditional and retained in history.
 
+#### Ask-policy prompt section
+
+```markdown
+<!-- dsh-user-approval-policy:ask -->
+```
+
+#### Never-policy prompt section
+
+```markdown
+Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
+<!-- dsh-user-approval-policy:never -->
+```
+
 ### Tool outcome
 
 **What the model sees**: `approval/asked` and `approval/decided` are log-only. The model sees only the asking consumer's eventual allowed, rejected, cancelled, or unavailable tool outcome; the human permission UI is not context.