docs: stop citing two hivectl commands that do not exist

mcp.md called it `hivectl choom`; the verb is `hivectl agent <name>
choom`. observability.md cited `hivectl shell`, which has never existed
at any level — the sentence only needs a shell, so it names one instead of
guessing which command an operator reaches for.

Found by subtracting the generated hivectl-cli.md's command headings from
every hivectl citation in docs/. Re-running it after the fix drops the
candidate list from 16 to 14, losing exactly these two.

Closes #4159

docs/scheduler/observability.md

@@ -191,7 +191,7 @@ The harness sets the OTLP variables (`OTEL_EXPORTER_OTLP_ENDPOINT`, `_PROTOCOL`,
 wide** — in systemd's `DefaultEnvironment` and in `/etc/profile` — so every
 process in an agent container exports to the hive's collector without any
 per-tool wiring. That covers Claude Code, `hive-metric`, and anything you run
-yourself from a tool call or `hivectl shell`.
+yourself from a tool call or a shell you open in the container.
 
 Every agent's export therefore includes these resource attributes
 automatically:

docs/turn-loop/mcp.md

@@ -221,7 +221,7 @@ task-id tracking) instead of an interactive shell. The harness gate is
 `--tools` / `--allowedTools` (Bash absent from `ALLOWED_BUILTIN_TOOLS`),
 so Bash never exists in a harness turn regardless of managed settings.
 `Bash` is deliberately **not** in the managed-settings deny so that the
-operator-driven `hivectl choom` session — which passes neither `--tools`
+operator-driven `hivectl agent <name> choom` session — which passes neither `--tools`
 nor `--allowedTools` — gets claude's built-in synchronous `Bash` tool
 (inline, human-approved). That sidesteps the async `mcp__bash__run`
 completion wake landing in the wrong session (the harness inbox) for a