Skip to main content
Glama
DeepSeek Harness MCP Server

DeepSeek Harness MCP Server

dsh_cancel_task

Idempotent

Cancel a task, clear pending permissions, and stop its Harness process. Existing file changes remain, so inspect them before retrying.

Instructions

Cancel the task, cancel pending permissions, and stop its Harness process. Existing file changes remain; inspect them before retrying. Repeated cancellation of a finished task is safe.

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": {
      "task_id": "<task_id>"
    },
    "name": "dsh_cancel_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare readOnly=false, destructive=false and idempotent=true, yet the description still adds substantive behavior: pending permission requests are cancelled, the Harness process is stopped, and existing file changes persist afterward. That persistence note is critical pre-call knowledge for a mutating tool and is consistent with destructiveHint=false rather than contradicting it.

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?

Three short sentences, each earning its place: the action, the post-state warning, and the idempotency guarantee. The effects are front-loaded before the caveats.

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

Completeness4/5

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

For a single-parameter mutation with no output schema, it covers effects, residual state, and repeat-call safety well. It stops short of stating what a call returns (e.g., resulting task status) or any permission requirements, which would matter when the operation spawns a cancellation flow.

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?

There is one required parameter with 0% schema description coverage; the schema only conveys type string with uuid format and a regex pattern. The description never explains that task_id identifies the task to cancel or whether a finished/unknown ID is acceptable, though the idempotency sentence partially compensates.

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

Purpose4/5

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

The description uses a specific verb and resource ('cancel the task') and enumerates the concrete effects (pending permissions, Harness process), which clearly separates it from read/submit siblings like dsh_get_task and dsh_submit_task. It does not explicitly name an alternative tool, so it falls short of the top mark.

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

Usage Guidelines4/5

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

It gives real usage context: inspect remaining file changes before retrying, and repeated cancellation of an already-finished task is safe. What it lacks is any when-not-to-use condition or explicit pointer to a sibling (e.g., checking status first via dsh_get_task).

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