From 64baa617ecf7aa5fd60aef0bf1f7562db00a38bf Mon Sep 17 00:00:00 2001
From: AbdulSamad94 <abdulsamadsiddiqui2000@gmail.com>
Date: Sun, 5 Oct 2025 00:51:19 +0500
Subject: [PATCH 1/2] docs: improve formatting consistency in tools
 documentation

---
 docs/tools.md | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/docs/tools.md b/docs/tools.md
index 38199c581..249c4a7f2 100644
--- a/docs/tools.md
+++ b/docs/tools.md
@@ -288,9 +288,9 @@ async def run_my_agent() -> str:
 
 In certain cases, you might want to modify the output of the tool-agents before returning it to the central agent. This may be useful if you want to:
 
-- Extract a specific piece of information (e.g., a JSON payload) from the sub-agent's chat history.
-- Convert or reformat the agent’s final answer (e.g., transform Markdown into plain text or CSV).
-- Validate the output or provide a fallback value when the agent’s response is missing or malformed.
+-   Extract a specific piece of information (e.g., a JSON payload) from the sub-agent's chat history.
+-   Convert or reformat the agent’s final answer (e.g., transform Markdown into plain text or CSV).
+-   Validate the output or provide a fallback value when the agent’s response is missing or malformed.
 
 You can do this by supplying the `custom_output_extractor` argument to the `as_tool` method:
 
@@ -369,15 +369,17 @@ asyncio.run(main())
 ```
 
 The `is_enabled` parameter accepts:
-- **Boolean values**: `True` (always enabled) or `False` (always disabled)
-- **Callable functions**: Functions that take `(context, agent)` and return a boolean
-- **Async functions**: Async functions for complex conditional logic
+
+-   **Boolean values**: `True` (always enabled) or `False` (always disabled)
+-   **Callable functions**: Functions that take `(context, agent)` and return a boolean
+-   **Async functions**: Async functions for complex conditional logic
 
 Disabled tools are completely hidden from the LLM at runtime, making this useful for:
-- Feature gating based on user permissions
-- Environment-specific tool availability (dev vs prod)
-- A/B testing different tool configurations
-- Dynamic tool filtering based on runtime state
+
+-   Feature gating based on user permissions
+-   Environment-specific tool availability (dev vs prod)
+-   A/B testing different tool configurations
+-   Dynamic tool filtering based on runtime state
 
 ## Handling errors in function tools
 

From 2b0b5f5d6e741c8d95c88d7e679f8cb747d615b2 Mon Sep 17 00:00:00 2001
From: Kazuhiro Sera <seratch@openai.com>
Date: Sun, 5 Oct 2025 09:16:41 -0700
Subject: [PATCH 2/2] Apply suggestions from code review

---
 docs/tools.md | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/docs/tools.md b/docs/tools.md
index 249c4a7f2..0acb2cb4a 100644
--- a/docs/tools.md
+++ b/docs/tools.md
@@ -288,9 +288,9 @@ async def run_my_agent() -> str:
 
 In certain cases, you might want to modify the output of the tool-agents before returning it to the central agent. This may be useful if you want to:
 
--   Extract a specific piece of information (e.g., a JSON payload) from the sub-agent's chat history.
--   Convert or reformat the agent’s final answer (e.g., transform Markdown into plain text or CSV).
--   Validate the output or provide a fallback value when the agent’s response is missing or malformed.
+- Extract a specific piece of information (e.g., a JSON payload) from the sub-agent's chat history.
+- Convert or reformat the agent’s final answer (e.g., transform Markdown into plain text or CSV).
+- Validate the output or provide a fallback value when the agent’s response is missing or malformed.
 
 You can do this by supplying the `custom_output_extractor` argument to the `as_tool` method:
 
@@ -370,16 +370,16 @@ asyncio.run(main())
 
 The `is_enabled` parameter accepts:
 
--   **Boolean values**: `True` (always enabled) or `False` (always disabled)
--   **Callable functions**: Functions that take `(context, agent)` and return a boolean
--   **Async functions**: Async functions for complex conditional logic
+- **Boolean values**: `True` (always enabled) or `False` (always disabled)
+- **Callable functions**: Functions that take `(context, agent)` and return a boolean
+- **Async functions**: Async functions for complex conditional logic
 
 Disabled tools are completely hidden from the LLM at runtime, making this useful for:
 
--   Feature gating based on user permissions
--   Environment-specific tool availability (dev vs prod)
--   A/B testing different tool configurations
--   Dynamic tool filtering based on runtime state
+- Feature gating based on user permissions
+- Environment-specific tool availability (dev vs prod)
+- A/B testing different tool configurations
+- Dynamic tool filtering based on runtime state
 
 ## Handling errors in function tools