add call_capability

docs/wf_mcp_proxy_reality_and_roadmap.md

@@ -126,8 +126,8 @@ When the exposed tool catalog grows large or changes often, FastMCP's search
 transform is a good mitigation: keep a stable pinned control/workflow spine
 visible, and use `search_tools` plus its synthetic `call_tool` for the changing
 rest of the catalog. Do not confuse that synthetic raw-tool caller with a
-future workflow-capability test tool; testing a normalized `NodeSpec` contract
-is a separate operation and should also remain pinned once it exists.
+workflow-capability test tool; `wf.workflow.call_capability` tests a normalized
+`NodeSpec` contract and remains pinned for that reason.
 
 ## What Is Probably Not Worth Owning Yet
 

docs/workflow_capabilities.md

@@ -266,11 +266,11 @@ Today:
 - `wf.mcp` owns workflow-facing MCP runtime helpers
 - discovered upstream tools can already become workflow node specs
 - saved artifacts can be tagged with `kind="workflow"` or `kind="wrapper"`
+- `wf.workflow.call_capability` can execute one planner-visible workflow
+  capability directly and return normalized `outcome` / `output`
 
 Not yet implemented:
 
-- a direct public tool for calling arbitrary workflow node specs for authoring
-  tests
 - per-outcome output schemas
 - graph-as-node for saved workflows