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

TECHNIQUE

Function calling / skills (API wrapping)

Tool Use & Structured Output

4APPLICATIONS
9OBSERVED OPERATORS
01

State of Practice

CROSS-VALIDATED — 6 OPERATORS

Function calling is deployed as constrained tool/API wrappers around search, graph, code, workflow, and business-system capabilities, with operators adding orchestration and validation to keep tool use reliable.

Observed Practices

Wrap internal/product capabilities as callable tools rather than relying on a free-form LLM alone.

6 of 6 operators with cited teardown evidence in this pool.
DropboxGrabLinkedInShopifyBlockAppFolio

Use tool calls to connect LLM apps to internal systems and external APIs.

4 of 6 operators with cited teardown evidence in this pool.
GrabLinkedInBlockDropbox

Expose retrieval/search as a tool or tool-backed service so agents can ground responses in indexed content.

3 of 6 operators with cited teardown evidence in this pool.
DropboxGrabLinkedIn

Put tool calling inside an orchestration layer: graph executors, workflow frameworks, query engines, or migrator runtimes select steps and route tool use.

6 of 6 operators with cited teardown evidence in this pool.
GrabShopifyLinkedInBlockDropboxAppFolio

Constrain tool context and tool choice to reduce model confusion: inject only relevant hints, collapse retrieval into one purpose-built tool, or split work into discrete steps.

4 of 6 operators with cited teardown evidence in this pool.
DropboxBlockShopifyGrab

Add structured-output, retry, caching, debugging, or feedback mechanisms around tool-calling workflows.

2 of 6 operators with cited teardown evidence in this pool.
ShopifyAppFolio

Where Operators Converge

Every cited operator deploys function calling as a bounded interface to concrete capabilities: retrieval indexes, plugins/APIs, graph services, file/code tools, workflow nodes, or business-product actions.

Every cited operator pairs tool use with some form of task-specific orchestration rather than presenting the tool call as an isolated API call.

Where Operators Diverge

Operators differ in how broad the exposed tool surface is.

APPROACH 01

Collapse many retrieval options into one aggregated search/index tool.

Dropbox

APPROACH 02

Offer modular plugins, Native Tools, Community Built Tools, and user-defined HTTP endpoints.

Grab

APPROACH 03

Expose a domain backend service through tool calling and convert the result into strict search filters.

LinkedIn

APPROACH 04

Expose codebase and execution capabilities as tools inside developer workflows.

ShopifyBlock

Operators differ in their orchestration style for tool-calling workflows.

APPROACH 01

Planning agent delegates retrieval query construction to a specialized search agent.

Dropbox

APPROACH 02

Graph-based executor and ReAct agents run nodes, edges, states, branching, looping, and modularity.

Grab

APPROACH 03

Declarative YAML workflows and markdown prompts sequence tool use and share transcripts across steps.

Shopify

APPROACH 04

A separate migrator process selects files, builds prompts, and invokes a model that calls back into diagnostics and test tools.

Block

APPROACH 05

A query engine uses Tool Calling when querying a fine-tuned LLM.

LinkedIn

APPROACH 06

LangGraph is used to aggregate responses from different nodes for the user.

AppFolio

Watch Items

Too much tool or retrieval context can make agentic systems harder to use reliably; observed mitigations include trimming context, collapsing retrieval into one tool, injecting only relevant hints, and splitting prompts into discrete steps.

Naive tool-using agents were reported as unreliable for large code or migration tasks; operators added diagnostics, tests, deterministic steps, steering messages, and policy/hints from repeated failures.

Tool-calling systems introduce operational overhead; cited deployments mention increased compute requirements, duplicate-work reduction with KV caching, and keeping test processes warm behind RPC.

02

Implementation Menu

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

Observed in Production

4 APPS