Bump version to 1.15.0

CHANGELOG.md

@@ -2,21 +2,31 @@
 
 All notable changes to TokenSaver.Mcp are documented here.
 
-## [Unreleased]
+## [1.15.0] — 2026-06-16
 
 ### Changed — stripped to a warm-start tool set
 - Reduced the advertised MCP surface from 11 tools to **3**: `OutlineCSharpFile`
   (structural warm start), `MinifyFile` (whole-file, all languages), and
   `TraceDiRegistrations` (DI wiring — the one discovery grep can't do cleanly).
   The focus/trace family (`FocusMethod`, `FocusMultipleMethods`,
   `FocusMethodsAcrossFiles`, `FocusType`, `FocusCallers`, `TraceCallers`,
-  `TraceImplementors`, `MapProject`) is no longer registered as an MCP tool.
-- Fixed per-session overhead dropped **4,134 → 1,504 tokens** (−64%):
-  `ServerInstructions` rewritten for the 3-tool set and 8 tool schemas removed.
+  `TraceImplementors`, `MapProject`) is no longer registered as an MCP tool (#99).
+- Fixed per-session overhead dropped **4,134 → 1,415 tokens** (−66%):
+  `ServerInstructions` rewritten for the 3-tool set, 8 tool schemas removed, and a
+  legacy duplicate `focus_method` registration (`FocusedEmissionTool`) deleted.
   Rationale: a controlled A/B (outline-only vs full toolset vs no-MCP) showed the
   focus/trace tools added no measured token value on scoped tasks; the durable win
   is a cheap structural warm start, after which `Grep` + a narrow `Read` of the
-  outline's line-ranges does the rest.
+  outline's line-ranges does the rest. On a real cheaper-model task this flips the
+  session ledger from net-negative to net-positive.
+- Removed the Markdown emitter.
+
+### Documentation
+- Reframed the README, NuGet readme, viewer pages, `llms.txt`, and registry
+  description around the warm start: it curbs wasteful reading, with the biggest win
+  on smaller/cheaper models (~8%) and large files. Dropped the "30–95% for everyone"
+  framing — the win scales inversely with model capability (~1% top-tier, ~5–7%
+  mid-tier, ~8% cheaper).
 
 ## [1.14.1] — 2026-06-11
 

mcp/TokenSaver.Mcp.csproj

@@ -13,7 +13,7 @@
     <PackAsTool>true</PackAsTool>
     <ToolCommandName>tokensaver-mcp</ToolCommandName>
     <PackageId>TokenSaver.Mcp</PackageId>
-    <Version>1.14.1</Version>
+    <Version>1.15.0</Version>
     <Authors>Sebastian Larsson</Authors>
     <Description>MCP server for .NET developers — gives AI assistants a token-efficient view of C#, VB, Razor, and .NET project files using the Roslyn compiler platform. Reduces tokens by 50-95% with no loss of logic.</Description>
     <PackageTags>mcp;dotnet;csharp;visualbasic;razor;roslyn;copilot;tokens;llm;tokensaver</PackageTags>

server.json

@@ -2,17 +2,17 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.Byggarepop/tokensaver",
   "title": "TokenSaver",
-  "description": "Token-efficient C#, Razor, and .NET file views for AI assistants. 50-95% token reduction via Roslyn.",
+  "description": "A structural warm start for AI coding agents in .NET — a cheap Roslyn signature map of C#/Razor/.NET files so the model reads only what it needs. Biggest win on smaller/cheaper models and large files.",
   "repository": {
     "url": "https://github.com/Byggarepop/TokenSaver",
     "source": "github"
   },
-  "version": "1.14.1",
+  "version": "1.15.0",
   "packages": [
     {
       "registryType": "nuget",
       "identifier": "TokenSaver.Mcp",
-      "version": "1.14.1",
+      "version": "1.15.0",
       "runtimeHint": "dnx",
       "runtimeArguments": [
         {