Tool definition
A structured description of a capability Claude can invoke.
Exam context: It gives Claude a predictable interface for external actions. When: Claude needs to interact with an external system or capability. When not: When no external action or structured capability is required.
See also: 8.1 Tool Implementation
Input schema
A structured specification of the arguments a tool accepts.
Exam context: It constrains and clarifies tool inputs. When: Defining or validating tool calls. When not: Never rely only on free-form text when structured inputs are required.
See also: 8.1 Tool Implementation
Tool dispatch
The process that receives a tool request and routes it to the appropriate implementation.
Exam context: It connects Claude's requested action to actual execution. When: Building an agentic harness or tool runtime. When not: When the application has no executable tools.
See also: 8.1 Tool Implementation
Approval pattern
A control that requires confirmation before a consequential tool action executes.
Exam context: It reduces the risk of unintended external actions. When: Tools can modify data, communicate externally, or create significant consequences. When not: For genuinely read-only and low-risk operations where approval adds unnecessary friction.
See also: 8.1 Tool Implementation
MCP server
A server that exposes tools, resources, and/or prompts through the MCP protocol.
Exam context: It provides a standardized interface between AI applications and external capabilities. When: When an application needs reusable external capabilities through MCP. When not: When a simple internal function is sufficient and no MCP integration is required.
See also: 8.2 MCP Server Development
MCP tool
An executable capability exposed by an MCP server.
Exam context: It allows the client or model-driven application to request an external action. When: When the application needs to perform an operation against an external system. When not: For information that should only be read as contextual data; a resource may be more appropriate.
See also: 8.2 MCP Server Development
MCP resource
A capability for exposing contextual or readable data through MCP.
Exam context: It separates data retrieval from executable actions. When: When the application needs external information or context. When not: When the primary requirement is to perform a state-changing operation.
See also: 8.2 MCP Server Development
MCP prompt
A reusable prompt template exposed through an MCP server.
Exam context: It standardizes common interaction patterns. When: When multiple clients can benefit from a reusable prompt workflow. When not: When the requirement is direct external execution or data retrieval.
See also: 8.2 MCP Server Development
stdio transport
A local communication mechanism using standard input and output streams.
Exam context: It allows a client to communicate with a locally launched MCP server process. When: For local MCP server integrations. When not: When clients need to reach a separately deployed remote server.
See also: 8.2 MCP Server Development
Remote MCP server
An MCP server deployed separately from the client and accessed over a network.
Exam context: It allows shared or centralized capabilities to be accessed by clients. When: When multiple applications or users need access to a shared service. When not: When a local process is simpler and sufficient.
See also: 8.2 MCP Server Development
Built-in tool
A capability already provided by the Claude environment or agent runtime.
Exam context: It can satisfy common requirements without additional custom implementation. When: When an existing built-in capability already meets the requirement. When not: When the application needs a specific operation that the available built-in capabilities do not provide.
See also: 8.3 Agentic Customization
Custom tool
An application-defined executable capability exposed to Claude.
Exam context: It allows Claude to request application-specific operations. When: When the application needs a new executable operation. When not: When an existing built-in capability already satisfies the requirement or when the requirement is primarily reusable instructions.
See also: 8.3 Agentic Customization
Skill
Reusable instructions, knowledge, or workflow guidance for an agent.
Exam context: It allows recurring task procedures to be captured and reused. When: When the main requirement is reusable guidance or a domain-specific workflow. When not: When the application needs direct executable access to an external system.
See also: 8.3 Agentic Customization
MCP
A standardized protocol for connecting compatible clients with external capabilities.
Exam context: It provides a reusable integration boundary for tools, resources, and prompts. When: When external capabilities need a standardized and reusable integration. When not: When a simple application-local function or existing capability is sufficient.
See also: 8.3 Agentic Customization
Agentic customization
The mechanisms used to extend or shape an agent's available capabilities and behavior.
Exam context: Different requirements call for different levels and types of customization. When: When deciding how to add capabilities, instructions, or integrations to an agent. When not: When no additional capability or behavior customization is required.
See also: 8.3 Agentic Customization