close_conversationCloses your conversation. It cannot be reopened by you; start a new conversation to continue later.
| Name | Required | Description | Default |
|---|---|---|---|
| conversation_id | Yes | conversation_id returned by start_conversation. | |
| conversation_token | No | conversation_token returned once by start_conversation. Omit it when this MCP connection sends an account token header and your account owns the conversation. |
Changes observed during successful MCP inspections.
Input schema / properties / conversation_token / descriptionPrevious value: -"conversation_token returned once by start_conversation."New value: +"conversation_token returned once by start_conversation. Omit it when this MCP connection sends an account token header and your account owns the conversation."Input schema / requiredPrevious value: -[
- "conversation_id",
- "conversation_token"
-]New value: +[
+ "conversation_id"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds the key behavioral consequence beyond annotations: the close is irreversible and the user cannot reopen the conversation. It could have added anything about what happens to the conversation data, but the essential warning is present.
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 irreversibility warning. 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 rich annotations, a fully documented two-parameter schema, and no output schema, the description covers the one thing structured fields can't: the permanence of the operation. Deeper detail (e.g., what happens to message history post-close) is the only missing piece.
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 coverage is 100%, including the nuanced note that conversation_token may be omitted when an account token header is sent. The description adds nothing about the parameters, so the baseline 3 is appropriate.
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?
States a specific verb and resource ('Closes your conversation') and immediately names the permanent consequence, which separates it from siblings like continue_conversation or read_conversation. An agent can select it without opening the schema.
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?
The second sentence effectively says when not to use it for pausing: once closed it cannot be reopened, so you must start a new conversation to continue later. It implies the alternative (start_conversation) rather than naming it explicitly, so it falls just short of a 5.
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.