Skip to main content
Glama
Huawei DCS MCP
by key-well

ListFlavors

ListFlavors
Read-onlyIdempotent

Query available Huawei DCS cache flavors by engine, version, capacity, CPU type, and instance mode to identify compatible Redis or Memcached specifications for provisioning or resizing.

Instructions

查询产品规格(只读查询)

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ListFlavors"
  }
}

Input Schema

NameRequiredDescriptionDefault
engineNo缓存引擎类型。取值范围如下: - Redis - Memcached
regionNoOverrides HUAWEI_REGION.
capacityNo缓存容量(G Byte)。 - Redis3.0:单机和主备类型实例取值:2、4、8、16、32、64。Proxy集群实例规格支持64、128、256、512和1024。 - Redis4.0和Redis5.0:单机和主备类型实例取值:0.125、0.25、0.5、1、2、4、8、16、32、64。Cluster集群实例规格支持24、32、48、64、96、128、192、256、384、512、768、1024。 - Memcached:单机和主备类型实例取值:2、4、8、16、32、64。
cpu_typeNoCPU架构类型。取值范围如下: - x86_64:X86架构 - aarch64:ARM架构
spec_codeNo产品规格编码。
cache_modeNo缓存实例类型。取值范围如下: - single:表示单机实例 - ha:表示主备实例 - cluster:表示cluster集群实例 - proxy:表示Proxy集群实例 - ha_rw_split: 表示读写分离实例
project_idNoOverrides HUAWEI_PROJECT_ID.
instance_idNo缓存实例ID,根据该字段可查询出实例可变更的规格
engine_versionNo缓存版本,当缓存引擎为Redis时,取值范围如下: - 3.0 - 4.0 - 5.0

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.5/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the parenthetical "(只读查询)" adds nothing new. With annotations covering the safety profile, the description still says nothing about result shape, whether the list is paginated or region-scoped, or that region defaults to the HUAWEI_REGION environment variable. For a 9-parameter query tool it is behaviorally silent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

At a single short clause it is certainly not verbose, but the parenthetical only duplicates an annotation, so not every element earns its place. The size is under-specified rather than concise: it is short because information is missing, not because the content was trimmed.

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

Completeness2/5

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

With 9 optional parameters and full schema coverage, the description could reasonably stay lean on inputs, but it should still convey what the tool returns and why the filters matter, since there is no output schema. As written, an agent knows only that it queries product specs read-only, leaving the practical workflow (pick a flavor before creating or resizing a cache instance) unstated.

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%, with every parameter including engine, capacity, cache_mode, spec_code and the region/project_id environment overrides thoroughly documented in the schema itself. The description adds no meaning beyond that – notably it never highlights instance_id as the switch that converts this into a changeable-spec query. Baseline 3 is appropriate when the schema does all the work.

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

Purpose3/5

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

The description pairs the verb "查询" with the resource "产品规格", matching the tool name ListFlavors, so the basic operation is identifiable. However, "product specifications" is vague on its own – it never says these are cache-instance flavors, nor that results feed instance creation or resizing decisions, which is the reason an agent would call it. No sibling differentiation is needed here since no other flavor-listing tool exists, but the purpose statement stays thin.

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

Usage Guidelines2/5

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

The only guidance is "只读查询", which merely restates the readOnlyHint annotation rather than telling the agent when to prefer this tool. There is no hint that passing instance_id narrows results to specs an existing instance can change to, nor any mention of calling this before create/resize flows. Usage context is left entirely to inference.

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