Skip to main content
Glama

Interrupt turn

dsh_interrupt
DestructiveIdempotent

Stop the currently running turn as if the user pressed stop, marking it cancelled while keeping partial output and leaving the conversation ready for a new task.

Instructions

Stop without saying anything new: interrupt the turn the conversation is running (ACP's native session/cancel, the same path as a user pressing stop). The interrupted turn is recorded as cancelled; the text and tool calls it had produced stay in its result (dsh_get / sentinel), and files it changed are not rolled back. The conversation itself stays healthy and can take a new task right away. To stop and redirect use dsh_interject; to cancel a queued task that has not started use dsh_queue(action=remove).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "conversation_id": "<conversation_id>"
    },
    "name": "dsh_interrupt"
  }
}

Input Schema

NameRequiredDescriptionDefault
conversation_idYesConversation id, from dsh_start or dsh_list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.8
    • changedInput schema / properties / conversation_id / description
      Previous value: -"会话 id,来自 dsh_start 或 dsh_list。"New value: +"Conversation id, from dsh_start or dsh_list."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing what happens to in-flight state: the turn is recorded as cancelled, produced text and tool calls remain in its result, file changes are not rolled back, and the conversation stays healthy for a new task. This concretely explains the destructiveHint and idempotentHint flags rather than merely repeating them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each carrying distinct information: the action, the resulting state, the non-rollback consequence, and the sibling routing. The key semantic ('stop without saying anything new') is front-loaded and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter interrupt tool with no output schema, the description covers everything an agent needs: trigger, mechanism, post-state, side effects, and where to inspect the cancelled turn (dsh_get / sentinel). No material gap remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single conversation_id property is already described in-schema as coming from dsh_start or dsh_list. The description refers to 'the conversation' but adds no new format or provenance detail beyond what the schema states, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific action (interrupt the running turn) and anchors it to a concrete mechanism (ACP native session/cancel, equivalent to a user pressing stop), while explicitly contrasting itself with dsh_interject and dsh_queue. An agent can pick this tool over its siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use and when-not-to-use routing: use dsh_interject to stop and redirect, use dsh_queue(action=remove) to cancel a task that has not started. The 'stop without saying anything new' opener frames the exact scenario this tool is for.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.