Skip to main content
Glama
eMCP for Evolution CMS

eMCP for Evolution CMS

Official

Files Tool

amount.files

Lists offloaded files for a selected rule with pagination, path search, and status filtering; returned file IDs can be used to recall or delete remote files.

Instructions

Read-only. What is offloaded for one rule: 50 files per page (newest first) with id, local_path, remote_path, size, status (pending/uploaded/failed/...), visibility and url. Only files the manager can still see in the file manager appear. Use q to search by path, page to continue (see pages). The id values feed amount.recall and amount.delete_remote.

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": {
      "rule": "<rule>"
    },
    "name": "amount.files"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoPart of the local path, e.g. "backup"
pageNoPage number, from 1
ruleYesRule uuid from amount.rules
statusNoOnly this status, e.g. "uploaded"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does so well: it declares read-only, fixes page size at 50 and ordering as newest-first, enumerates the returned fields, and discloses the visibility filter ('only files the manager can still see'). It does not state permission requirements or what happens when a rule has zero offloaded files, which keeps it out of 5 territory.

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?

Dense and front-loaded — 'Read-only' and the page-size/ordering facts come first, and every clause carries information. The colon-and-list construction in the opening sentence is slightly awkward to parse, but there is no filler or repetition.

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?

There is no output schema, so the description must describe the return shape, and it does: field list, page size, ordering, status values, and the `pages` pagination signal. What remains unstated is minimal for a simple paged list — mainly error/empty behavior and whether the 50-per-page size is configurable.

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 a 3 is the baseline, but the description adds real meaning beyond the schema: `page` is tied to the returned `pages` value, `q` is confirmed as path-substring search, and the significance of the returned `id` (it feeds recall/delete_remote) is only stated here. The `status` filter is only illustrated by the field enumeration rather than explained directly.

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

Purpose4/5

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

The description names a specific resource and scope: files offloaded for one rule, 50 per page, newest first. An agent can tell this is a rule-scoped file listing rather than a general browse. The phrasing 'What is offloaded for one rule' is slightly elliptical, and no sibling listing tool is explicitly contrasted, so it stops short of a 5.

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?

It gives actionable in-tool guidance: use `q` to search by path and `page` to continue via `pages`, and it flags that returned `id` values feed amount.recall and amount.delete_remote. That is operational routing, not true when-to-use/when-not guidance — there is no explicit statement of when another listing tool would be preferable or any precondition beyond the required rule uuid.

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