diff --git a/codex-rs/core/src/tools/spec.rs b/codex-rs/core/src/tools/spec.rs
index 3364d19e8..afa4c1861 100644
--- a/codex-rs/core/src/tools/spec.rs
+++ b/codex-rs/core/src/tools/spec.rs
@@ -853,7 +853,10 @@ fn create_spawn_agent_tool(config: &ToolsConfig) -> ToolSpec {
         name: "spawn_agent".to_string(),
         description: format!(
             r#"
-        Only use `spawn_agent` if and only if the user explicitly asked for sub-agents or parallel agent work. Spawn a sub-agent for a well-scoped task. Returns the agent id (and user-facing nickname when available) to use to communicate with this agent. This spawn_agent tool provides you access to smaller but more efficient sub-agents. A mini model can solve many tasks faster than the main model. You should follow the rules and guidelines below to use this tool.
+        Only use `spawn_agent` if and only if the user explicitly asks for sub-agents, delegation, or parallel agent work.
+        Requests for depth, thoroughness, research, investigation, or detailed codebase analysis do not count as permission to spawn.
+        Agent-role guidance below only helps choose which agent to use after spawning is already authorized; it never authorizes spawning by itself.
+        Spawn a sub-agent for a well-scoped task. Returns the agent id (and user-facing nickname when available) to use to communicate with this agent. This spawn_agent tool provides you access to smaller but more efficient sub-agents. A mini model can solve many tasks faster than the main model. You should follow the rules and guidelines below to use this tool.
 
 {available_models_description}
 ### When to delegate vs. do the subtask yourself
diff --git a/codex-rs/core/tests/suite/spawn_agent_description.rs b/codex-rs/core/tests/suite/spawn_agent_description.rs
index ad822805a..117d1d9ef 100644
--- a/codex-rs/core/tests/suite/spawn_agent_description.rs
+++ b/codex-rs/core/tests/suite/spawn_agent_description.rs
@@ -180,6 +180,24 @@ async fn spawn_agent_description_lists_visible_models_and_reasoning_efforts() ->
         !description.contains("Hidden Model"),
         "hidden picker model should be omitted from spawn_agent description: {description:?}"
     );
+    assert!(
+        description.contains(
+            "Only use `spawn_agent` if and only if the user explicitly asks for sub-agents, delegation, or parallel agent work."
+        ),
+        "expected explicit authorization rule in spawn_agent description: {description:?}"
+    );
+    assert!(
+        description.contains(
+            "Requests for depth, thoroughness, research, investigation, or detailed codebase analysis do not count as permission to spawn."
+        ),
+        "expected non-authorization clarification in spawn_agent description: {description:?}"
+    );
+    assert!(
+        description.contains(
+            "Agent-role guidance below only helps choose which agent to use after spawning is already authorized; it never authorizes spawning by itself."
+        ),
+        "expected agent-role clarification in spawn_agent description: {description:?}"
+    );
 
     Ok(())
 }