Skip to main content
Glama

Add Storage Remote Files

add_storage_remote_files
Destructive

[write, queued] Add files to a storage account (storages_account_id or storages_account_uuid) from public https URLs instead of uploading bytes. urls is a list (max 20); path is the folder (empty = zone root); file_name names the file when exactly one URL is given (else the URL's own file name is used); description (up to 500 characters) is saved with every file once it is stored (see list_storage_files). Allowed: png, jpg, jpeg, gif, webp, svg, pdf, doc(x), xls(x), ppt(x), odt, txt, md, xml, rss, css, js, mp4; max 100 MiB each. The URLs are queued and a worker downloads them one at a time, oldest first, then notifies the merchant. Returns the queued rows (storages_remote_upload_id) and the URLs that were rejected; follow the progress with list_storage_remote_files.

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": {
      "urls": "<urls>"
    },
    "name": "add_storage_remote_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
urlsYes
file_nameNo
descriptionNo
storages_account_idNo
storages_account_uuidNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / description
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Description"
      +}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that the operation is queued and asynchronous, that a worker downloads one URL at a time oldest-first, that the merchant is notified, the 20-URL cap, the 100 MiB per-file cap, the allowed extension list, and that rejected URLs are returned. This is exactly the context an agent needs for a destructive, non-idempotent write.

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 the write/queued tag and the core action, then parameter semantics, then constraints, then return behavior. It is a single dense paragraph, so the constraint list and return-value sentence are harder to scan than they could be, but no sentence is wasted.

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?

With no output schema, the description still explains what is returned (queued rows with storages_remote_upload_id plus rejected URLs) and how to track completion. For a 6-parameter async write tool, nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does: urls is a list capped at 20, path is the folder with empty meaning zone root, file_name only applies when exactly one URL is given (otherwise the URL's own name is used), description is capped at 500 characters and stored per file, and the account is identified by id or uuid.

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 ('Add files to a storage account ... from public https URLs instead of uploading bytes') and immediately distinguishes itself from byte-upload and from the sibling list_storage_remote_files used for progress.

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?

Makes the selection condition explicit ('from public https URLs instead of uploading bytes') and routes the agent to list_storage_remote_files to follow progress. It does not state exclusions such as when to prefer a direct upload tool or what to do when a URL is rejected beyond the return value.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources