Utility Tools 101

StackOne Utility Tools: intelligent search→execute routing that reduces token bloat, improves tool‑selection accuracy, and scales to thousands of actions.

Utility Tools are a special category of StackOne tools that help agents find and use the right tool at the right time, without overwhelming the model.

Why Utility Tools

The Problem: Modern LLMs struggle when presented with too many tools in their context window. Every tool definition consumes tokens, bloats prompts, and dilutes reasoning ability.

Key Issues:

• Accuracy drops when choosing between hundreds of tools (MTU‑Bench, ToolACE, BFCL v3)
• Context limits hit quickly; “Lost in the Middle” shows long prompts degrade reasoning
• Provider caps: OpenAI/Vertex limit ~128 tools/functions (OpenAI community)

The Solution: More tools ≠ more capability. Without structure, they become noise. Utility Tools solve this.

How It Works

Search → Execute Pattern

Utility Tools act as an intelligent router:

1. Search – tool_search semantically matches user requests to relevant tool(s)

   • Powered by BM25 and Orama-style indexing for fast search across thousands of tools
   • Example: “fetch employee ID 123” → returns employee.get tool

2. Execute – tool_execute calls chosen tool(s) with right inputs

   • Agent only sees relevant tools, not the entire catalog

This keeps agent prompts lean while expanding their capabilities.

Evidence

Research Sources: Accuracy decreases as candidate tool sets grow and with multi-turn complexity.

• MTU‑Bench (ICLR’25): accuracy drops as turns/tools increase (Fig. 5)
• ToolACE (2024/25): error correlates with #candidate APIs (Fig. 2)
• Broader evals: BFCL v3, Gorilla, Databricks show tool-pool pitfalls

Examples

Real-World Use Cases:

• HR Agent: “Approve Alice’s time off request” → finds hibob_create_time_off → executes in HiBob
• Support Agent: “Search for Jira ticket ABC‑123” → finds ticketing_ticket_list → returns details
• Knowledge Agent: “Find training docs on GDPR” → finds documents_file_search → queries KB

When to Use: ✅ Agent spans many SaaS systems (dozens→thousands of tools) ✅ Need higher selection accuracy and scalability ❌ Very small, static toolset

Core Benefits

Scales Effortlessly

Access thousands of tools without token bloat or context overflow

Improves Accuracy

Only relevant tools exposed per request, reducing misfires and hallucinations

Account-Aware

Only returns tools relevant to configured Account IDs, respecting auth and governance controls

Composable

Works with unified actions (HRIS, ATS, LMS, Documents, IAM)

Utility tools enable AI agents to dynamically discover and execute the right tools without hardcoding tool names. This is particularly useful for building flexible AI assistants that can handle various user requests intelligently.

Architecture Overview

Utility tools consist of two main functions:

• tool_search: Searches for relevant tools based on natural language queries using BM25 semantic search
• tool_execute: Executes discovered tools with the provided parameters

How It Works

Benefits

• Dynamic Discovery: No need to hardcode tool names or maintain static lists
• Multi-Tenant Ready: Agents adapt to available integrations per customer
• Natural Language: Search tools using descriptive queries
• Intelligent Routing: BM25 algorithm finds the most relevant tools automatically

TypeScript Implementation

In the TypeScript SDK, utility tools are implemented using:

• Orama Database: Fast in-memory search index for tool discovery
• BM25 Algorithm: Statistical ranking function for relevance scoring
• Native TypeScript Types: Full type safety for tool parameters and responses

Read more: For guidance on using utility tools in TypeScript, including advanced use cases, multi-agent workflows, and framework integrations, see Utility Tools.

Next Steps

• Get started with utility tools - Practical implementation guide
• Advanced Utility Tools usage - Framework integration patterns
• OpenAI integration - Use utility tools with OpenAI
• Vercel AI SDK - Stream utility tool responses