fix(tools): do not index tools, only index toolgroups (#2261)

When registering a MCP endpoint, we cannot list tools (like we used to)
since the MCP endpoint may be behind an auth wall. Registration can
happen much sooner (via run.yaml).

Instead, we do listing only when the _user_ actually calls listing.
Furthermore, we cache the list in-memory in the server. Currently, the
cache is not invalidated -- we may want to periodically re-list for MCP
servers. Note that they must call `list_tools` before calling
`invoke_tool` -- we use this critically.

This will enable us to list MCP servers in run.yaml

## Test Plan

Existing tests, updated tests accordingly.

docs/_static/llama-stack-spec.html

@@ -9555,9 +9555,6 @@
                     "toolgroup_id": {
                         "type": "string"
                     },
-                    "tool_host": {
-                        "$ref": "#/components/schemas/ToolHost"
-                    },
                     "description": {
                         "type": "string"
                     },
@@ -9599,21 +9596,11 @@
                     "provider_id",
                     "type",
                     "toolgroup_id",
-                    "tool_host",
                     "description",
                     "parameters"
                 ],
                 "title": "Tool"
             },
-            "ToolHost": {
-                "type": "string",
-                "enum": [
-                    "distribution",
-                    "client",
-                    "model_context_protocol"
-                ],
-                "title": "ToolHost"
-            },
             "ToolGroup": {
                 "type": "object",
                 "properties": {