Skip to main content
Glama

Stop this task's own SDK process and preserve its evidence (destructive)

dsh_cancel_task
Destructive

Stops the SDK process for a specific delegated task and verifies the PID is gone, interrupting the turn without affecting the user's running DSH Desktop. Returns the observed diff.

Instructions

Stops the SDK process this bridge started for THIS task only, then verifies the pid is gone. It never touches the user's running DSH Desktop. Because the SDK has no per-turn cancel, the turn is interrupted rather than gracefully cancelled, and files may already have been partly modified; the returned diff is what the bridge actually observed.

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

Input Schema

NameRequiredDescriptionDefault
reasonNo
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so safety is partly covered; the description adds real value beyond that by disclosing that the turn is interrupted rather than gracefully cancelled, that files may already be partly modified, and that the returned diff reflects only what the bridge observed. It does not cover permission requirements or whether the interruption itself is reversible, 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.

Conciseness4/5

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

Three tight sentences, front-loaded with the action and its scope, then consequences. Every clause carries information relevant to correct invocation, with no filler or repetition of the title.

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 destructive two-parameter tool with no output schema, the description covers scope, interruption semantics, partial-modification risk, and the nature of the returned diff. The only notable gap is that neither parameter is described, which matters given the zero schema coverage.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry parameter meaning, but it only implies a target via 'THIS task only' and never mentions the optional 'reason' parameter or its 2000-character cap. An agent gets no guidance on what to supply for taskId format or when to pass a reason.

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 names a specific verb ('Stops') and a precisely scoped resource ('the SDK process this bridge started for THIS task only'), plus the follow-up verification step. The scoping clause ('never touches the user's running DSH Desktop') effectively separates it from a general desktop-level stop, though no sibling tool is named explicitly.

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

Usage Guidelines3/5

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

Usage is implied by the scope statement: use this to end the current task's own SDK process. The note that the SDK has no per-turn cancel explains why interruption rather than graceful cancellation occurs, which is contextual but not a when-to-use/when-not-to-use rule. No alternative (e.g., dsh_recover_task or dsh_wait_task) is named as a contrasting choice.

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