“tool calling”的搜索结果

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementations. The LLM never sees your code - it only sees the schema and description. Use when "agent tool, function calling, tool schema, tool design, mcp server, mcp tool, tool use, build tool for agent, define function, input_schema, tool_use, tool_result, agents, tools, function-calling, mcp, json-schema, anthropic, openai, llm-tools" mentioned.

中文简介正在准备中。当前显示原文说明。

Automate Callingly operations through Rube MCP, a connection to external tools. Discover available actions and their required inputs, verify the account connection, and execute tasks using the tool definitions returned by the search.

中文简介正在准备中。当前显示英语简介。

• Find available Callingly actions
• Check the account connection before running tasks
• Run a sequence of Callingly operations

Automate Callingly operations through Rube MCP, a connection to external tools. Discover available actions and their required inputs, verify the account connection, and execute tasks using the tool definitions returned by the search.

中文简介正在准备中。当前显示英语简介。

• Find available Callingly actions
• Check the account connection before running tasks
• Run a sequence of Callingly operations

Diagnose why an AI agent skips tools, passes incorrect arguments, or repeats calls. Get guidance on tool descriptions, schemas that define accepted inputs, execution flow, and mock tests before connecting to a real model.

中文简介正在准备中。当前显示英语简介。

• Finding why an agent never calls a tool
• Fixing incorrect or missing tool arguments
• Investigating repeated calls or skipped steps

Design tools that AI agents can understand and call correctly. Covers JSON Schema, a format for defining inputs, along with clear descriptions, input examples, validation, and error responses that help agents recover from failures.

中文简介正在准备中。当前显示英语简介。

• Designing inputs for an AI agent tool
• Improving tool descriptions and input examples
• Reviewing validation and error responses

Provides and generates LangChain4j tool and function calling patterns: annotates methods as tools with @Tool, configures tool executors, registers tools with AiServices, validates tool parameters, and handles tool execution errors. Use when building AI agents that call tools, define function specifications, manage tool responses, or integrate external APIs with LLM-driven applications.

中文简介正在准备中。当前显示原文说明。

Design tools that AI agents can understand and call, covering input schemas, clear descriptions, validation, and error handling. The guidance includes JSON Schema, a format for defining inputs, and MCP, a protocol for connecting agent tools.

中文简介正在准备中。当前显示英语简介。

• Design inputs for a new agent tool
• Improve tool descriptions that guide model choices
• Review validation and error handling

Test Model Context Protocol (MCP) servers and tool-calling systems for security vulnerabilities including tool injection, parameter manipulation, privilege escalation, and data exfiltration through AI agent tool interfaces. Use this skill when assessing MCP server implementations, AI agent tool integrations, or any system that exposes tools to language models. Covers tool confusion attacks, cross-tool exploitation, and MCP server hardening assessment.

中文简介正在准备中。当前显示原文说明。

Use n8n-mcp tools to find workflow steps, check settings, and create or update automations. Provides guidance on tool arguments, templates, folders, credentials, and security audits so agents can choose appropriate operations.

中文简介正在准备中。当前显示英语简介。

• Finding nodes and checking their settings
• Creating and updating workflows
• Finding and deploying workflow templates

Use n8n-mcp tools to find workflow steps, check settings, and create or update automations. Provides guidance on tool arguments, templates, folders, credentials, and security audits so agents can choose appropriate operations.

中文简介正在准备中。当前显示英语简介。

• Finding nodes and checking their settings
• Creating and updating workflows
• Finding and deploying workflow templates

Use the command line to discover and run tools on MCP servers, which connect agents to external systems. Inspect required inputs, pass JSON arguments, and retrieve results as JSON or raw text for scripts.

中文简介正在准备中。当前显示英语简介。

• Listing available MCP servers and tools
• Searching for tools by name
• Checking tool inputs before calling an external API

Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.

中文简介正在准备中。当前显示英语简介。

• Building a chatbot with conversation memory
• Connecting external tools to an AI agent
• Returning data in a defined JSON format

Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.

中文简介正在准备中。当前显示英语简介。

• Building a chatbot with conversation memory
• Connecting external tools to an AI agent
• Returning data in a defined JSON format

Add AI chat, text generation, and agents to applications using AI SDK. The skill checks documentation and source code to guide streaming replies, external tool calls, structured results, React integration, and fixes for outdated API usage.

中文简介正在准备中。当前显示英语简介。

• Add AI chat to an application
• Build an agent that calls external tools
• Build answers using retrieved documents

Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.

中文简介正在准备中。当前显示原文说明。

Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the *tool surface* is an LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling, tool_use, MCP, LangChain `@tool`, CrewAI `BaseTool`). Encodes the *what to surface, how to name, how to shape, how to fail* — not any single framework's API. ~80% of agent tools in production are HTTP wrappers; this is the SOP for getting them right.

中文简介正在准备中。当前显示原文说明。

Implement circuit breaker logic for agentic tool calls — tracking tool health, transitioning between closed/open/half-open states, reducing task scope when tools fail, routing to alternatives via capability maps, and enforcing failure budgets to prevent error accumulation. Separates orchestration (deciding what to attempt) from execution (calling tools), following the expeditor pattern. Use when building agents that depend on multiple tools with varying reliability, designing fault-tolerant agentic workflows, recovering gracefully from tool outages mid-task, or hardening existing agents against cascading tool failures.

中文简介正在准备中。当前显示原文说明。

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

中文简介正在准备中。当前显示原文说明。

Configure tools and skills for sub-agents before dispatching development tasks. Role presets cover implementation, planning, reviews, testing, and verification, with defined boundaries for what each agent should do and whether it may modify files.

中文简介正在准备中。当前显示英语简介。

• Setting tool permissions before spawning a sub-agent
• Separating implementation, planning, and review roles
• Configuring agents for review without file changes

Build Claude tool use (function calling) workflows with the Messages API. Use when implementing tool use, function calling, agent loops, or building AI assistants that interact with external systems. Trigger with phrases like "claude tool use", "anthropic function calling", "claude tools", "agent loop anthropic", "tool_use blocks".

中文简介正在准备中。当前显示原文说明。

Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI agents.

中文简介正在准备中。当前显示原文说明。

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

中文简介正在准备中。当前显示原文说明。

Build AI applications with LangChain, including chatbots with conversation history and systems that search documents before answering. The skill provides examples for connecting models, calling tools, retrieving information, and tracing application runs.

中文简介正在准备中。当前显示英语简介。

• Building a chatbot that uses conversation history
• Creating a question-answering system for documents
• Developing an agent that calls external tools

Design AI agents that plan tasks, call tools, and retain useful information. Covers coordination between agents, evaluation, and debugging, with practical patterns for execution limits, error handling, and tracing what an agent does.

中文简介正在准备中。当前显示英语简介。

• Designing an agent that plans and executes tasks
• Organizing tool definitions and selection
• Deciding what an agent should remember