Remove a knowledge collection from an AI agent.
The collection and its files are not deleted — only the agent assignment is removed.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | ID of the AI agent | |
| in_workspace | No | Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected. | |
| collection_id | Yes | ID of the collection to unassign |
Changes observed during successful MCP inspections.
Input schema / properties / in_workspaceAdded value: +{
+ "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+ "type": "integer"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds genuine value beyond them by clarifying scope: the collection and its files survive, only the assignment is removed. It does not cover auth requirements or whether re-running is safe, keeping it below a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the action and followed by the key scope caveat. Every sentence earns its place with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With full schema coverage, annotations covering safety hints, and no output schema, the description supplies the one piece of context an agent most needs: that this is not a destructive delete. It is complete enough to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all three parameters (agent_id, collection_id, in_workspace) are already documented in the schema. The description adds no additional meaning about parameter usage or format, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb+resource: 'Remove a knowledge collection from an AI agent.' This clearly identifies the assignment relationship being severed. The second sentence distinguishes it from a delete operation, though it does not name the inverse sibling (collections_assign_agent) explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit when-to-use clause or named alternative. The clarification that deletion is not involved implicitly tells the agent this is the right tool when only the assignment should go, but usage must be inferred rather than read.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.