Skip to main content
Glama
sjk4425

ncloud-mcp-server

by sjk4425
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

ncloud_ncs_head_object

Read-only

Check Ncloud Storage object metadata (size, type, ETag, version, lock status) via HEAD request. Returns exists=false for missing objects or delete markers instead of an error.

Instructions

[Ncloud Storage] Get an object's metadata without downloading it (HEAD /{key}): size, type, ETag, storage class, version ID, restore status and Object Lock retention / legal hold. Returns exists=false on 404 (object missing, or its current version is a delete marker on a versioned bucket) instead of an error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesObject key (path) to check
versionIdNoVersion ID of the object (versioning-enabled buckets). Omit for the current version
bucketNameYesName of the Ncloud Storage bucket

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.15.0
    • changedInput schema / properties / bucketName / description
      Previous value: -"Name of the bucket"New value: +"Name of the Ncloud Storage bucket"
    • addedInput schema / properties / versionId
      Added value: +{
+  "description": "Version ID of the object (versioning-enabled buckets). Omit for the current version",
+  "type": "string"
+}
  2. First observedv1.10.1

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses the most surprising behavioral trait: 'Returns exists=false on 404... instead of an error', including the subtle delete-marker-on-versioned-bucket case. It also clarifies the exact HTTP semantics (HEAD /{key}, no body download) and enumerates the metadata fields an agent can expect. These are genuinely non-obvious behaviors that materially change how an agent should interpret results.

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?

The core purpose is front-loaded in the first clause, and the trailing sentence covers the 404 edge case without waste. The field enumeration list makes the sentence dense, but every element earns its place since the metadata inventory serves as a return-value contract in the absence of an output schema.

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?

With no output schema, the description compensates well: it enumerates the metadata fields returned and specifies the not-found contract (exists=false, including the delete-marker nuance). For a simple 3-parameter tool with 100% schema coverage and a readOnly annotation, this covers what an agent needs to call it and interpret its result. The only gap is the exact response shape, which is minor given the field list.

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%: key, versionId, and bucketName each have meaningful descriptions in the schema itself. The tool description adds no parameter-level detail beyond the schema; it mentions 'version ID' as a returned field, which loosely relates to the versionId parameter, but that is incidental rather than explanatory. Baseline 3 applies since the schema carries the full burden.

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 states a specific verb and resource: 'Get an object's metadata without downloading it (HEAD /{key})'. The HTTP method and the listed return fields (size, ETag, storage class, version ID, restore status, Object Lock) make the tool's exact function unambiguous. It also distinguishes itself from siblings: unlike ncloud_ncs_get_object (which fetches content) and ncloud_ncs_get_object_attributes (a different API variant), this is the lightweight metadata HEAD operation.

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 context is implied rather than explicit: 'without downloading it' signals an agent to reach for this tool when metadata alone suffices, and the cheap HEAD semantics suggest a pre-check idiom. However, the description never names alternatives or states when not to use it, leaving the agent to infer the decision rule from sibling names.

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