HOME/TECHNIQUE/Tool Use & Structured Output/Function calling / skills (API wrapping)

TECHNIQUE

Function calling / skills (API wrapping)

Tool Use & Structured Output

5APPLICATIONS
10OBSERVED OPERATORS
01

State of Practice

CROSS-VALIDATED — 4 OPERATORS

Observed operators wrap proprietary systems, indexes, plugins, files, and graph services as callable tools inside LLM workflows rather than relying on standalone chat completions.

Observed Practices

Expose non-LLM systems as callable tools, plugins, or APIs for an LLM or agent to use at runtime.

4 of 4 operators with teardown evidence show this practice.
DropboxGrabLinkedInShopify

Wrap retrieval, graph, or knowledge-store access behind tool calls so the model can fetch grounded context or structured identifiers before search or answer generation.

3 of 4 operators with teardown evidence show tool/API wrapping around retrieval, graph, or knowledge access.
DropboxGrabLinkedIn

Package tool calling inside higher-level orchestration frameworks rather than leaving the model to decide everything in one prompt.

3 of 4 operators with teardown evidence show tool use embedded in orchestration frameworks, workflows, or sub-agent routing.
DropboxGrabShopify

Maintain tool catalogs or reusable tool layers so multiple apps or workflows can share integrations.

2 of 4 operators with teardown evidence show reusable tool catalogs or tool layers.
GrabShopify

Use tools for actions and code execution, not only information retrieval.

2 of 4 operators with teardown evidence show callable tools that execute code, schedule actions, write files, or run coding agents.
GrabShopify

Adopt MCP or discuss MCP alongside tool-calling infrastructure.

2 of 4 operators with teardown evidence explicitly mention MCP in connection with tool calling or agent/client interaction.
DropboxGrab

Where Operators Converge

Every operator with direct teardown evidence exposes at least one proprietary or operational capability to the LLM through a tool, plugin, API, or tool-calling pattern.

Where Operators Diverge

Operators differ in what they wrap as callable tools.

APPROACH 01

Search, index, and graph services are wrapped so the model can retrieve context or structured IDs.

DropboxLinkedIn

APPROACH 02

Business-system and external-API integrations are exposed as plugins or native/community tools.

Grab

APPROACH 03

Developer-workflow tools expose file reading, file writing, and coding-agent capabilities.

Shopify

Operators differ in how tool calls are orchestrated.

APPROACH 01

Agentic execution with sub-agents, ReAct agents, graph executors, or structured workflow orchestration.

DropboxGrabShopify

APPROACH 02

A query engine uses tool calling to classify intent, fetch external data, and construct search filters or embeddings.

LinkedIn

Watch Items

Unconstrained agents can be unreliable in large codebases; Shopify reported that letting AI “roam free around millions of lines of code” did not work well and that non-determinism hurt reliability.

Advanced LLM use behind tool-calling systems can raise serving cost and infrastructure requirements; LinkedIn reported increased compute requirements and investment in GPU infrastructure, KV caching, and fused kernels.

Tool-wrapped retrieval still depends on content understanding quality; Dropbox reported that complex images need true multimodal understanding and audio clips need transcription before they are useful to the system.

02

Implementation Menu

CURATED DEFAULTS
NameKindMaturity
Provider-native function callingservicecommodity
Zod/Pydantic-derived tool schemaslibrarycommodity
03

Observed in Production

5 APPS