Skip to main content
Glama
eMCP for Evolution CMS

eMCP for Evolution CMS

Official

Fetch Tool

amount.fetch

Downloads files or entire folders from a storage mount into a site folder in the background and returns a run UUID for tracking progress.

Instructions

Download a file, or the files in a folder (recursive=true keeps subfolders, up to 2000 files; else the files directly inside, up to 200), from a storage mount into a site folder, in the background; returns a run uuid for amount.status. The mount may be one of the person's own computers (amount.computers): "from my computer mypc, folder 2025/08 of sqlbackups, into backups" is mount="mypc", remote="sqlbackups/2025/08", to="backups", recursive=true. When a name is taken here, a newer file replaces an older one only if destructive tools are allowed for this call; otherwise it is kept, and every file not written is listed with its reason in amount.status. Never writes executable files; the destination must be a folder the manager can modify; files from a computer fill a site folder only up to its quota.

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": {
      "mount": "<mount>",
      "remote": "<remote>",
      "to": "<to>"
    },
    "name": "amount.fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesSite folder to download into, e.g. "assets/backup"
siteNoThe site the person named ("site.com"): refused if this installation does not serve it.
mountYesMount uuid (preferred) or name
remoteYesRemote file or folder, e.g. "Backups/db-2026-10-16.sql.gz"
recursiveNoInclude subfolders, recreating them under `to`. Default false.
on_conflictNo"skip" keeps a file already here; "newer" lets a newer file replace an older one (needs destructive permission). Default: newer when destructive tools are allowed, else skip.
delete_remoteNoDelete the remote copy after a verified download (destructive). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

With only readOnlyHint=false available, the description carries real weight: background execution with a run uuid, overwrite semantics gated on destructive permission, unwritten files reported with reasons in amount.status, a ban on executable files, a writable-destination requirement, and quota limits. These are behavioral traits an agent cannot derive from annotations or schema.

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 purpose, limits and return handle are front-loaded in the first clause, and the examples are compact. It is dense but every sentence adds operational detail; the conflict-handling sentence mildly restates the on_conflict schema description, which is the only redundancy.

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?

For a 7-parameter, non-read-only tool with no output schema, the description covers everything an agent needs: asynchronous return with a status handle, file-count ceilings, overwrite policy, failure reporting, and safety constraints. Nothing material is left to inference.

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, but the description adds meaning beyond it: recursive=true is quantified (up to 2000 files with subfolders recreated, 200 otherwise), and the conflict default is tied to whether destructive tools are permitted. The mount-to-computer correspondence is shown by example rather than explained generically, which is the only real gap.

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: download a file or folder from a storage mount into a site folder, in the background, returning a run uuid for amount.status. It distinguishes file vs folder behavior and points at the sibling that consumes the result, so an agent can place it precisely among amount.browse, amount.deliver and amount.status.

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?

Gives a concrete invoked scenario ("from my computer mypc, folder 2025/08 of sqlbackups, into backups") that shows how a natural-language request maps onto mount/remote/to/recursive, plus the reference to amount.computers for mounts. It stops short of explicitly saying when to prefer this over siblings such as amount.deliver or amount.files, but the usage context is clear.

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