Skip to main content
Glama

sockdock_stop_run

DestructiveIdempotent

Cancel a run that is taking too long: it stops execution and posts a "stopped" reply in its thread. Already-completed edits and commands are not undone.

Instructions

Stops a run in progress and posts a "stopped" reply in its thread; the answer it had so far is not posted. What the run already did (files edited, commands run) is not undone, and the next reply in the thread starts a new run. Get the run's id from sockdock_get_status or sockdock_list_runs; for a run that has already ended it returns an error and changes nothing. Use it when the user asks to cancel something that is taking too long.

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": {
      "id": "<id>"
    },
    "name": "sockdock_stop_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesid of a run whose status is running (running[].id in sockdock_get_status, or id in sockdock_list_runs)

Output Schema

NameRequiredDescriptionDefault
okYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.1
    • changedInput schema / properties / id / description
      Previous value: -"the run's id"New value: +"id of a run whose status is running (running[].id in sockdock_get_status, or id in sockdock_list_runs)"
  2. First observedv0.2.0

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 explaining what partial output is lost ('the answer it had so far is not posted'), that side effects are NOT rolled back ('what the run has already did... is not undone'), and how subsequent thread replies behave. That is exactly the context an agent needs before choosing a destructive, idempotent action.

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 compact sentences, front-loaded with the action and its effects, followed by id sourcing and then the usage trigger. No filler or restatement of the name.

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?

Output schema exists, so return values need not be explained; the description instead covers everything an agent must know before invoking a destructive, non-rollback stop: precondition, lost partial output, and non-undo of prior edits.

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 description coverage is 100% and the single parameter is already documented as a running run's id with its source, so the description adds little parameter-specific detail. It reinforces the source tools and the failure mode for an already-ended run, but does not add syntax or format beyond the schema.

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?

States a specific verb and resource ('Stops a run in progress') plus the observable side effect ('posts a "stopped" reply in its thread'). The scope is clear enough to distinguish it from siblings like stop/cancel of anything else and from read-only status tools.

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 an explicit trigger ('when the user asks to cancel something that is taking too long'), an explicit precondition failure ('a run that has already been ended returns an error and changes nothing'), and tells where to get the id from (sockdock_get_run / sockdock_list_runs).

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