Skip to main content
Glama
Sign In
BonengDriveMCP

BonengDriveMCP

by time32
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

execute_drive_run

Destructive

Runs an explicitly approved drive motion plan by taking PC control, sending speed and heartbeat commands, and returning a job ID for continuous mode or releasing control after a timed stop.

Instructions

仅在用户明确允许该计划实际运动时调用。申请 PC 控制权、发送带单位的速度和心跳；持续模式返回后台 job_id，用 get_drive_run_status 查询、stop_drive_pc_control 停止。限时模式结束 OFF1 停机后释放；失败不自动重试。

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": {
      "plan_id": "<plan_id>"
    },
    "name": "execute_drive_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
plan_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.1

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (destructive=true, non-idempotent, open-world), it discloses that the call takes PC control, sends a heartbeat, behaves differently in continuous mode (returns a background job_id) versus timed mode (ends with OFF1 stop then releases control), and does not auto-retry on failure. These are consequential behaviors an agent cannot infer from the schema or annotations.

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?

The permission gate is front-loaded, followed by mechanics and then failure/lifecycle behavior. Every clause carries distinct information (control acquisition, heartbeat, mode-dependent return, shutdown, no retry) with 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 destructive motion tool, the description covers the gate condition, control handoff, mode-dependent returns, follow-up tools, and failure semantics. Since an output schema exists, return-value details need not be spelled out, and the one-clause mention of job_id is sufficient.

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 a single parameter, plan_id, with 0% schema description coverage. The description refers to 'the plan' implicitly linking plan_id to a plan produced upstream (plan_drive_run), which adds some meaning, but it never states the id's origin or format explicitly, so the gap is only partially closed.

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?

The description uses a specific verb+resource combination: it actually executes a planned drive run, takes PC control, sends a speed value with units and a heartbeat. It is clearly distinct from the sibling planning tools (plan_drive_run, plan_drive_position_move) and from the status/stop tools, so an agent can place it in the workflow without opening other schemas.

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?

It opens with an explicit precondition gate ('only call when the user explicitly permits the plan to actually move') and then routes the agent to the correct follow-up tools: get_drive_run_status for the background job and stop_drive_pc_control to stop. When-to-use, what-to-do-after, and the stop path are all named.

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

Deploy Server

Other Tools