Skip to main content
Glama

ensp_smart_config

Send configuration commands sequentially to eNSP devices; on failure, diagnose the command and return repair suggestions, optionally stopping to prevent cascading errors.

Instructions

智能配置下发:逐条下发命令,遇到错误时自动诊断并提供修复建议。

ensp_send_commands 的区别:

  • 每条命令执行后,若 errored=True 自动调用诊断引擎

  • 返回中包含每条失败命令的 diagnosis 字段

  • stop_on_error=True 时首条失败即停止,避免级联错误

  • auto_gather_llm_context=True 时,失败后自动收集设备全貌供 LLM 深度推理

参数:

  • session_id_or_name:会话 ID 或设备名

  • commands:命令列表

  • stop_on_error:遇错即停(推荐 True)

  • auto_diagnose:自动对失败命令执行规则诊断(默认 True)

  • auto_gather_llm_context:失败后自动收集设备全貌生成 LLM 推理上下文(默认 False)

  • experiment_description:用户实验需求描述(用于 LLM 推理上下文)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandsYes
auto_diagnoseNo
stop_on_errorNo
session_id_or_nameYes
experiment_descriptionNo
auto_gather_llm_contextNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: per-command execution, automatic diagnosis engine invocation on errored=True, first-failure termination via stop_on_error, and optional device-context gathering for LLM reasoning. It does not address permission requirements, persistence of pushed config, or rate/throughput limits, leaving some behavioral gaps.

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?

Well structured with a summary line, a difference block, and a parameter block; the core purpose is front-loaded. Slightly verbose in repeating parameter names already in the schema, but each line earns its place.

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?

An output schema exists, so return values need not be fully spelled out, though the description usefully notes the diagnosis field per failed command. All parameters are explained and the sibling distinction is addressed, so an agent has what it needs to call correctly; auth and side-effect details remain unstated.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate, and it documents all six parameters with meaning and defaults (auto_diagnose default True, auto_gather_llm_context default False, experiment_description purpose). Descriptions are terse but sufficient; no format examples for commands or session identifier.

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 (智能配置下发 - smart config push of commands) and immediately names the sibling it must not be confused with (ensp_send_commands), enumerating concrete behavioral differences. An agent can distinguish it from the sibling without opening either schema.

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?

The comparison block makes the selection condition clear (use this when you want per-command auto-diagnosis and optional LLM context gathering), and it recommends stop_on_error=True to avoid cascading errors. It stops short of an explicit 'use X instead of Y when' statement, so it's strong context but not fully prescriptive.

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