openai · OpenAI Platform Docs
Tool search
Implements dynamic tool loading by allowing a model to search for and inject tool definitions into its context on demand to reduce token usage and costs.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Tool search
Implements dynamic tool loading by allowing a model to search for and inject tool definitions into its context on demand to reduce token usage and costs.
When To Use
Use when you need to manage large numbers of tool definitions without exceeding context limits or incurring high token costs for unused tool schemas.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/tool-search-workflow-guide.md | A guide explaining how to use tool search to dynamically load tool definitions into a model's context to optimize token usage. | Questions about a guide explaining how to use tool search to dynamically load tool definitions into a model's context to optimize tok... |
What This Skill Covers
- Tool search allows the model to dynamically search for and load tools into the model's context as needed. This allows you to avoid loading all tool definitio...
- Main sections:
Use namespaces where possible,Tool search types,Hosted tool search,Client-executed tool search,Advanced usage.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/tools-tool-search.md
