StackOne actions are exposed to agents as tools — an action in the catalog becomes a tool in your agent’s hands. The two terms describe the same operation from either side.
- Burns tokens — every tool definition consumes context before the agent does any work
- Hurts accuracy — LLMs make worse tool selections as the candidate set grows; more tools without structure become noise
- Hits provider caps — OpenAI caps function definitions at ~128 per request
- Search - finds actions by natural language
- Execute - runs the action returned by Search.
Key features
Scales to thousands of tools
Search returns only the relevant actions for each query, however large the catalog.
Improves accuracy
Only relevant tools exposed per request, reducing misfires and hallucinations.
Account-aware
Filters results to tools available for configured account IDs, respecting authentication boundaries.
Framework-ready
Returns a Tools collection with converters for OpenAI, LangChain, Vercel AI SDK, and more.
What it saves
Loading every tool definition scales with your catalog — hundreds of actions can run to hundreds of thousands of tokens before the agent does any work. Search & Execute keeps that footprint flat: two tools, whatever the catalog size.Individual tools — 500 tools loaded · ~150,000 tokens
Search & Execute — 2 tools · ~900 tokens
Illustrative — exact counts depend on the actions enabled and the model.
Example flows
When to use it
Use Search & Execute when your agent spans many SaaS systems — dozens to thousands of tools — or targets models with limited context windows. For a small, focused action set where you want the model to see every tool, use individual tools instead.Agent Setup
Turn it on in your agent’s client — ready-to-paste configs for ChatGPT, Claude, Cursor, and more.
Tool Discovery
Embedding StackOne into your own code? Implement Search & Execute and the other discovery methods.