Added a way to switch off tools you never need (#1115)

app/MindWork AI Studio/Tools/ToolCallingSystem/AGENTS.md

@@ -19,3 +19,5 @@ Tool implementations must treat model-provided arguments as untrusted input. Val
 A tool which belongs to a preview feature returns false from `IToolImplementation.IsAvailable` while the preview is switched off; the registry then leaves it out of every list, every request, and the token count, so no component has to check that preview for the tool. Every tool declares in `IToolImplementation.OutboundData` where its arguments go: a chat which holds internal content, such as mails, passages of a data source, a search of the wiki, or an internal web page, keeps the tools whose data goes further than its restriction allows from being offered and from running, see `ToolSelectionRules.IsOutboundDataAllowed`. A tool which brings internal content into the chat raises `ToolExecutionResult.RequiredOutboundDataRestriction`, next to `RequiredProviderConfidence` and `RequiredDataSecurity`, names the source in its `OutboundDataOrigin`, and tells the model beforehand that it may end web search, worded by `WebSearchFirstRule`. "Outbound Data Restrictions" in `documentation/Tools.md` explains the sources and the levels, and "Searching Mailboxes" there the mail tools.
 
 A tool which offers itself from the context of a chat instead of being selected, such as `semantic_search`, sets `Activation = ToolActivation.CONTEXT` and tailors its function to each request in `ResolveFunctionAsync`.
+
+A tool needs nothing of its own to be switched off by the user or by an organization: `ToolRegistry.IsToolActive` checks both `DataTools.UserDisabledToolIds` and `DataTools.DisabledToolIds` for every tool, and the organization comes first. Keep it that way; a check which asks only one of the two lists lets a switched-off tool through. "Switched-Off Tools" in `documentation/Tools.md` explains the rest.