tool
In plain wordsAny outside capability an AI model is allowed to use — a web search, a calculator, a code runner, a database or an app — described to the model so it can ask for it by name.
- 1
Agents
A capability external to a large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. that the model can invoke through its host application: a function, web API, command-line program, database query, browser action, or another model or agent. A tool is presented to the model as a definition — a name, a natural-language description of what it does and when to use it, and an input schema, usually in JSON SchemaJSON Schema, prop. n.: A standard way of writing down exactly what a piece of JSON data must look like — which fields, of which types — so that software and AI models can check it or follow it. — and the model uses it by emitting a tool calltool call, n.: A single request from an AI model to use one of its tools — naming the tool and filling in the details — which the surrounding software then carries out and reports back on. that the harnessharness, n.: The software around an AI model that gives it instructions and tools, carries out its actions and decides when it stops. The model is the engine; the harness is the rest of the car. executes. Tools may be client-side (run by the developer's code), server-side (run by the model provider, such as hosted web search or code execution) or published by MCP serversMCP server, n.: A small program that makes some service — say a database, a calendar or a company's internal tools — available to any AI assistant that speaks the Model Context Protocol.. Because the model chooses tools from their descriptions, naming, wording and granularity strongly affect reliability — the concern of agent–computer interfaceagent–computer interface, n.: The commands, tools and feedback designed for an AI agent to work with a computer — the agent's version of a user interface, shaped around how language models read and act. design — and agents with hundreds of tools may load definitions on demand rather than all at once.
Give the agent a read-only database tool before you give it one that can write.
- 2
AI risk
In debates about AI risk, a system that answers or acts only when directed, as opposed to an agent pursuing goals of its own; see tool AItool AI, n.: AI built to be used like an instrument, answering, suggesting or calculating when asked, rather than pursuing goals on its own. Some argue that this is the only kind we should build., the proposal that advanced AI be built only in this form.
Origin
For language models, the 2022–2023 papers MRKLMRKL system, n.: An early design, pronounced 'miracle', in which a language model acts as a switchboard, sending each part of a question to the right specialist — a calculator, a database, a search tool — and combining the answers., ReActReAct, prop. n.: A method in which an AI alternates between thinking out loud about what to do next and taking an action, such as a web search, then uses what it observed to plan its next step. and ToolformerToolformer, prop. n.: A 2023 Meta research model that learned on its own when a tool — a calendar, a translator, a search engine, a calculator — would help it predict text, keeping only the tool uses that actually paid off. cast external APIs as tools; OpenAI's ChatGPT pluginsChatGPT plugins, prop. n.: Add-ons, launched in 2023 and retired in 2024, that let ChatGPT use outside services — web browsing, a code runner, travel booking or shopping sites — while answering a user. (March 2023) and function callingfunction calling, n.: A feature of AI model services that lets the model reply with a neatly formatted request to run one of a program's functions, rather than with ordinary text; the program, not the model, then runs it. (June 2023) made tool definitions a standard API feature, and the Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI. (November 2024) standardized how tools are published and discovered.
Usage note
In APIs 'tool' and 'function' are near-synonyms; OpenAI's original 'functions' parameter gave way to a more general 'tools' parameter in late 2023. Tool descriptions are an attack surface: see tool poisoningtool poisoning, n.: Hiding harmful instructions in the description of a tool an AI assistant can use, so the assistant obeys them when it reads the tool's details, even though the user never sees them..
Related
- tool calltool call, n.: A single request from an AI model to use one of its tools — naming the tool and filling in the details — which the surrounding software then carries out and reports back on.
- tool usetool use, n.: An AI model's ability to reach beyond its own knowledge by operating outside tools — searching the web, running code, using a calculator or an app — and folding the results into its work.
- function callingfunction calling, n.: A feature of AI model services that lets the model reply with a neatly formatted request to run one of a program's functions, rather than with ordinary text; the program, not the model, then runs it.
- Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI.
- agent–computer interfaceagent–computer interface, n.: The commands, tools and feedback designed for an AI agent to work with a computer — the agent's version of a user interface, shaped around how language models read and act.
- tool poisoningtool poisoning, n.: Hiding harmful instructions in the description of a tool an AI assistant can use, so the assistant obeys them when it reads the tool's details, even though the user never sees them.
- tool AItool AI, n.: AI built to be used like an instrument, answering, suggesting or calculating when asked, rather than pursuing goals on its own. Some argue that this is the only kind we should build.
Sources
- Paniego, S. & Roy Gosthipaty, A. (2026). Harness, Scaffold, and the AI Agent Terms Worth Getting Right. Hugging Face blog. huggingface.co/blog/agent-glossary
Mentioned in
agentic AIagentic AI, n.: AI built to pursue goals on its own — planning, taking actions and adjusting along the way — instead of only responding to one prompt at a time. 'Agentic' describes how much of this independence a system has., AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done., chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going., model APImodel API, n.: A web service through which programs send requests to an AI model run by a company and receive its answers, usually paying per use instead of running the model themselves., Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI., promptprompt, n.: The message or instructions you give an AI system — a question, a request, some examples or a document — that it responds to. Clearer prompts generally get better results., agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks., agentic workflowagentic workflow, n.: A multi-step process in which AI models draft, check, use tools and revise their work over several rounds, instead of answering in one shot; often the steps are laid out by developers in advance., AI systemAI system, n.: A complete piece of technology that uses AI to do something, such as screening loan applications, driving a car or chatting with customers, including the AI model and the software around it., code executioncode execution, n.: Letting an AI write a small program and actually run it — to do math, analyze a spreadsheet or test its own code — then use the real output instead of guessing., context engineeringcontext engineering, n.: Managing an AI model's reading material: choosing, trimming and arranging the instructions, documents, tool results and memories it is given on every turn, so that it has what the task needs and little else., function callingfunction calling, n.: A feature of AI model services that lets the model reply with a neatly formatted request to run one of a program's functions, rather than with ordinary text; the program, not the model, then runs it., harnessharness, n.: The software around an AI model that gives it instructions and tools, carries out its actions and decides when it stops. The model is the engine; the harness is the rest of the car., JSON SchemaJSON Schema, prop. n.: A standard way of writing down exactly what a piece of JSON data must look like — which fields, of which types — so that software and AI models can check it or follow it., LangChainLangChain, prop. n.: A popular free software toolkit, and the company behind it, for building applications that connect AI language models to documents, databases, tools and multi-step workflows., MCP serverMCP server, n.: A small program that makes some service — say a database, a calendar or a company's internal tools — available to any AI assistant that speaks the Model Context Protocol., orchestrationorchestration, n.: Coordinating several AI calls, tools or agents so each does its part in the right order and their results are combined into one finished piece of work, as a conductor directs an orchestra., RL environmentRL environment, n.: A practice world built for training an AI by trial and error: it hands the AI tasks and tools, lets it act, and scores the results so the AI can learn what works., scaffoldingscaffolding, n.: The code, prompts and tools built around an AI model so it can carry out tasks it could not manage from a bare prompt — like the scaffolding that lets builders reach every part of a building., subagentsubagent, n.: A helper AI agent that a main agent starts to handle one piece of a job; it works in its own separate workspace and reports back a short summary when it is done., system promptsystem prompt, n.: Background instructions given to a chatbot before the conversation starts, setting its role, rules, tone and tools. Users usually never see it, but it shapes every reply., threat modelthreat model, n.: A clear statement of who might attack a system, what they want, what they know and what they can do — the yardstick for judging whether a defense is good enough., tool calltool call, n.: A single request from an AI model to use one of its tools — naming the tool and filling in the details — which the surrounding software then carries out and reports back on., tool usetool use, n.: An AI model's ability to reach beyond its own knowledge by operating outside tools — searching the web, running code, using a calculator or an app — and folding the results into its work.