[PR #3572] docs: add dynamic tool tradeoffs for cache and model behavior [closes DOC-991] #3615

Open
opened 2026-06-05 18:23:41 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3572
Author: @open-swe[bot]
Created: 4/14/2026
Status: 🔄 Open

Base: mainHead: open-swe/8d7b0026-5bc3-e1cf-bdfe-7b24d78c54d2


📝 Commits (3)

  • 5d8f20e docs: add dynamic tools explanation and common pitfalls section to agents page
  • b565ec8 docs: add dynamic tool tradeoffs covering cache invalidation and model behavior risks
  • 151bc61 Apply suggestion from @npentrel

📊 Changes

2 files changed (+111 additions, -3 deletions)

View changed files

📝 src/oss/langchain/agents.mdx (+104 -0)
📝 src/oss/langchain/middleware/custom.mdx (+7 -3)

📄 Description

Description

Adds a "Tradeoffs" subsection to the dynamic tools documentation addressing common questions: (1) models may attempt to call tools that were available in earlier turns but have since been removed, (2) changing the tool list invalidates the provider's prompt cache with practical mitigation strategies, and (3) fewer tools generally means better accuracy. Also adds a Warning callout to the middleware custom docs page cross-linking to the tradeoffs section.

Resolves DOC-991

Test Plan

  • Verify the new Tradeoffs section renders correctly in preview deployment
  • Confirm the Warning callout on the middleware custom page renders and links correctly

Opened collaboratively by Naomi Pentrel and open-swe.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/3572 **Author:** [@open-swe[bot]](https://github.com/apps/open-swe) **Created:** 4/14/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `open-swe/8d7b0026-5bc3-e1cf-bdfe-7b24d78c54d2` --- ### 📝 Commits (3) - [`5d8f20e`](https://github.com/langchain-ai/docs/commit/5d8f20e3ed2e96eabe69ea64152059d03ed81c18) docs: add dynamic tools explanation and common pitfalls section to agents page - [`b565ec8`](https://github.com/langchain-ai/docs/commit/b565ec8d6479af0f170473062498eeafd4580e19) docs: add dynamic tool tradeoffs covering cache invalidation and model behavior risks - [`151bc61`](https://github.com/langchain-ai/docs/commit/151bc61f4f296f0490572699b92a8b365ed4c77b) Apply suggestion from @npentrel ### 📊 Changes **2 files changed** (+111 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `src/oss/langchain/agents.mdx` (+104 -0) 📝 `src/oss/langchain/middleware/custom.mdx` (+7 -3) </details> ### 📄 Description ## Description Adds a "Tradeoffs" subsection to the dynamic tools documentation addressing common questions: (1) models may attempt to call tools that were available in earlier turns but have since been removed, (2) changing the tool list invalidates the provider's prompt cache with practical mitigation strategies, and (3) fewer tools generally means better accuracy. Also adds a Warning callout to the middleware custom docs page cross-linking to the tradeoffs section. Resolves DOC-991 ## Test Plan - [ ] Verify the new Tradeoffs section renders correctly in preview deployment - [ ] Confirm the Warning callout on the middleware custom page renders and links correctly _Opened collaboratively by Naomi Pentrel and open-swe._ --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 18:23:41 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#3615