Add tool execution to tool registry docs#296
Merged
Merged
Conversation
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
Jped
approved these changes
May 18, 2026
bb220
reviewed
May 18, 2026
bb220
reviewed
May 18, 2026
bb220
approved these changes
May 18, 2026
…usama/tool-execution-docs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
PromptLayer can now run a tool's body in a sandbox between LLM turns, so your prompt completes end-to-end without your app writing a tool-call loop.
What's new
New feature page
features/tool-registry/auto-execution.mdx, headline conceptual doc covering the tool-call loop, how PromptLayer drives it, body writing conventions (argsdict, body-only editor), supported languages, behaviour in prompts (single/multi/mixed tool calls + 10-iteration cap), errors split (user-code vs infra), sandbox security, and when to use vs not.New reference pages
reference/tool-registry-create-version.mdx—POST /api/public/v2/tool-registry/{identifier}/versionsreference/tool-registry-test-execute.mdx—POST /api/public/v2/tool-registry/{identifier}/test-executeWhat's updated
Feature pages
features/tool-registry/overview.mdx— added paragraph + link to the auto-execution pagefeatures/tool-registry/using-in-prompts.mdx— added "Auto Execution" subsectionReference pages
reference/tool-registry-create.mdx— note about the new optionalexecutionpayloadreference/tool-registry-get.mdx— note that response includesexecutionwhen presentOpenAPI spec (
openapi.json)POST /tool-registry/{identifier}/versions,POST /tool-registry/{identifier}/test-executePOST /tool-registry— added optionaldescriptionandexecutionto the bodyGET /tool-registry— addeddescriptionto each item's responseGET /tool-registry/{identifier}— addeddescriptionto the registry, mention ofexecutionon the versionNavigation (
docs.json)auto-executionto the Tool Registry feature grouptool-registry-create-versionandtool-registry-test-executeto the Tool Registry reference groupNew assets
images/tool-registry/test-run-dialog.pngimages/tool-registry/execution-editor-py.pngimages/tool-registry/execution-editor-js.pngimages/tool-registry/execution-toggle.pngIncidental fix
docs.json— replaced deprecatedadd-mcpenum value incontextual.optionswithmcp(Mintlify removedadd-mcpfrom the allowed list; was blockingmintlify dev).Test plan
mintlify devruns without errors/features/tool-registry/auto-executionrenders end-to-end, all 4 images visible with rounded corners, tabs (Python/JS) switch, code samples render/reference/tool-registry-create-versionand/reference/tool-registry-test-executerender with auto-generated request/response panels/features/tool-registry/auto-executionfrom overview, using-in-prompts, create, get, create-version, test-execute all resolve/reference/templates-get, other feature groups) still render — confirmsopenapi.json+docs.jsonweren't broken