Prerequisites
What are you trying to do that currently feels hard or impossible?
Nothing currently. This is just a nice thing to add.
Suggested Solution(s)
https://modelcontextprotocol.io/docs/concepts/tools#tool-definition-structure
According to the latest spec, tools can have the following annotations:
readOnlyHint?: boolean; // If true, the tool does not modify its environment
destructiveHint?: boolean; // If true, the tool may perform destructive updates
idempotentHint?: boolean; // If true, repeated calls with same args have no additional effect
openWorldHint?: boolean; // If true, tool interacts with external entities
Agents and users can use this to decide whether to run a tool.
In MCP Toolbox a tool that runs a select or fetches metadata should have the readOnly hint. A tool that runs INSERT/UPDATE/DELETE should have a destructive hint.
Alternatives Considered
No response
Additional Details
No response
Prerequisites
What are you trying to do that currently feels hard or impossible?
Nothing currently. This is just a nice thing to add.
Suggested Solution(s)
https://modelcontextprotocol.io/docs/concepts/tools#tool-definition-structure
According to the latest spec, tools can have the following annotations:
Agents and users can use this to decide whether to run a tool.
In MCP Toolbox a tool that runs a select or fetches metadata should have the readOnly hint. A tool that runs INSERT/UPDATE/DELETE should have a destructive hint.
Alternatives Considered
No response
Additional Details
No response