chore(1001): retire recover_half_written_items from MCP surface

The recovery tool was a one-shot migration aid for the half-written
items that existed before the Stage 1 allocator fix. The three live
orphans (989/1000/1001) have been migrated; the Stage 1 fix prevents
new half-writes; the tool's job is done.

Removes the MCP wrapper, schema, dispatch case, and tools-list
assertion. The db::recover module itself stays in-process (under
`#[allow(dead_code)]`) so it can be re-exposed quickly if the bug
ever resurfaces — its regression tests still run as part of the
default suite.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

server/src/http/mcp/dispatch.rs

@@ -93,8 +93,6 @@ pub async fn dispatch_tool_call(
         "purge_story" => story_tools::tool_purge_story(&args, ctx),
         // Debug CRDT dump (story 515)
         "dump_crdt" => diagnostics::tool_dump_crdt(&args),
-        // Recover half-written pipeline items (bug 1001)
-        "recover_half_written_items" => diagnostics::tool_recover_half_written_items(&args),
         // Read-only peer mesh diagnostics (story 720)
         "mesh_status" => diagnostics::tool_mesh_status(&args),
         // Arbitrary pipeline movement