Skip to main content
Glama

Create or List a Sirv Folder

sirv_cdn_manage_folder

Create folders in Sirv CDN or list folder contents to browse paths before uploading files.

Instructions

Create a folder, or list the contents of a folder, in the Sirv account connected to the workspace. action picks create or list.

Use list to browse Sirv paths, and create before you upload into a new folder. Do not use it for Studio library folders: use sirv_list_assets with folderId. To find files by name or tag in any folder, use sirv_cdn_search_files.

Inputs: folder_path is the full path, such as /products. continuation works with list only: pass the cursor from the page before.

create is queued, and Sirv makes the folder in the background; the answer does not say whether the folder existed already. list answers at once with contents (each item's filename, basename, dirname, contentType, size, mtime and isDirectory), total for this page, and continuation, which is null on the last page. A folder that does not exist returns FOLDER_NOT_FOUND.

Credits: free.

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": {
      "action": "<action>",
      "folder_path": "<folder_path>"
    },
    "name": "sirv_cdn_manage_folder"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgIdNoWorkspace id from sirv_list_organizations. Default: the workspace you signed in to
actionYescreate makes the folder; list returns its contents
folder_pathYesFull path of the folder in Sirv, such as /products
continuationNoFor list: the cursor from the previous page

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.1.1
    • changedInput schema / properties / action / description
      Previous value: -"Create the folder or list its contents"New value: +"create makes the folder; list returns its contents"
    • changedInput schema / properties / continuation / description
      Previous value: -"Cursor from a previous list call"New value: +"For list: the cursor from the previous page"
    • changedInput schema / properties / folder_path / description
      Previous value: -"Full Sirv folder path, such as /products"New value: +"Full path of the folder in Sirv, such as /products"
    • changedInput schema / properties / orgId / description
      Previous value: -"Organization ID (uses default org if omitted)"New value: +"Workspace id from sirv_list_organizations. Default: the workspace you signed in to"
    • addedInput schema / properties / orgId / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only supply generic flags (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description goes well beyond them: create is asynchronous/queued, the response does not reveal whether the folder already existed, list is synchronous with pagination via `continuation`, and a missing folder yields FOLDER_NOT_FOUND. The queued-create caveat is especially valuable because it explains the practical consequence behind idempotentHint=false.

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?

Front-loaded with purpose, then usage, then inputs, then return behavior, then credits — a clean hierarchy with short sentences. The 'Inputs:' block partially restates schema field descriptions ('full path, such as /products' appears in both), which is the only real redundancy; everything else earns its place.

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?

There is no output schema, and the description compensates by enumerating the list payload (filename, basename, dirname, contentType, size, mtime, isDirectory), the per-page total, the null-on-last-page continuation, and the FOLDER_NOT_FOUND error. For a two-mode tool with 4 parameters, an agent has everything needed to act and interpret results.

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 100%, so the baseline is 3; the definition still adds routing meaning by stating that `continuation` works with list only and is the cursor from the previous page, which maps parameters to actions rather than repeating field definitions. `orgId` is not mentioned in the description, but the schema fully documents it, so the omission is minor.

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 first sentence names a specific verb pair (create / list) and the exact resource (a folder in the connected Sirv account), and the second sentence ties each to the `action` enum. It further distinguishes itself from `sirv_list_assets` (Studio library folders) and `sirv_cdn_search_files` (search by name/tag), so an agent can route correctly without opening any schema.

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?

Explicit when-to-use for both modes: 'Use list to browse Sirv paths, and create before you upload into a new folder.' It adds an explicit when-NOT-to-use ('Do not use it for Studio library folders: use sirv_list_assets with folderId') and names the alternative for a related intent (sirv_cdn_search_files for name/tag lookup). Nothing about selection is left to inference.

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