#tool-calling

8 resources and 5 guides tagged #tool-calling on ChangeGamer.

Open-Weight Models for Agents · Reference
Cross-vendor comparison table of major open-weight LLM families — license, tool-calling support, context window, and agent-builder notes — as of July 2026.
Reliable Tool Calling and Structured Outputs · Guide
How providers guarantee schema-valid tool calls and structured output — mechanisms, failure modes, and mitigations — for production agent builders.
Evaluating AI Agents: Benchmarks and Methods · Reference
Why agent eval differs from single-turn LLM eval, a verified benchmark reference table (SWE-bench, GAIA, BFCL, tau-bench, WebArena, AgentBench, MLE-bench, OSWorld), and practical evaluation methods for agent builders.
Streaming Responses for Agents · Guide
Transport formats, provider event schemas, and practical concerns for consuming streamed LLM responses in production agents: SSE mechanics, OpenAI (Chat Completions and Responses API) and Anthropic event formats, partial-JSON tool-call parsing, backpressure, cancellation, and gateway proxying.
Testing AI Agents in CI · Guide
How to write deterministic, fast, CI-friendly tests for non-deterministic agents: the three-layer test pyramid, LLM mocking, cassette/VCR-style replay, snapshot testing of tool-call trajectories, pass@k thresholds, and verified tooling.
Synthetic Data Generation for Agent Training · Guide
How to build agentic training corpora without human annotation at scale: the three generation patterns (distillation, self-play, environment rollout), open pipelines (distilabel, AgentInstruct, APIGen-MT, TOUCAN), quality filtering, and the model-collapse risk.
MCP vs Function Calling: When to Use Which · Reference
Direct comparison of provider-native function/tool calling and the Model Context Protocol — architecture, decision criteria, and how they compose.
How to Choose an LLM for Agentic Tasks · Guide
A criteria-based decision framework for selecting an LLM for agent use: tool-calling reliability, long-context behavior, structured output, cost per task, latency, and a step-by-step selection procedure.

Guides

MCP Server in Production: How to Build, Ship and Run One · pillar guide
The operator playbook for taking an MCP server past the quickstart: transport choice, OAuth 2.1 auth, tool design, versioning against a moving spec, testing across clients, distribution, observability, cost and the failure modes that show up once real clients connect.
Defending MCP Clients Against Tool Description and Output Injection · guide
Two distinct MCP injection surfaces — a tool description at connect-time and a tool's return value at call-time — and the client-side architectural patterns (Dual LLM, Action-Selector, Context-Minimization) that contain each one.
How to Test an MCP Server in CI · guide
The implementation mechanics below the three-layer test pyramid: what a mocked MCP transport actually replaces, what a Streamable HTTP cassette contains, a concrete CI job/trigger shape, and how to catch spec-version drift before it reaches production.
Common MCP Server Failure Modes and How to Fix Them · guide
A runtime playbook for the two MCP server failure modes with no dedicated deep-dive elsewhere: unrecoverable state after a mid-call crash, and malformed or hallucinated tool calls that reach the handler despite upstream validation.
MCP Tools vs Resources vs Prompts: How to Choose the Right Primitive · guide
A decision procedure for MCP's three server-side primitives — who controls each one, a worked example of what it costs to expose a Resource as a Tool by mistake, and how Sampling and Elicitation fit as the client-side counterparts.