Skip to main content
Glama
eMCP for Evolution CMS

eMCP for Evolution CMS

Official

Recall Tool

amount.recall

Restores files previously offloaded by aMount to their original location or a specified site folder, with optional overwrite and a run UUID for status tracking.

Instructions

Bring files that aMount offloaded earlier back to the site (ids from amount.files, at most 200, all from the same rule). Background run: returns a run uuid for amount.status. Without to each file goes back to its original place; with to into that site folder. Never overwrites unless overwrite=true, never writes executable files, and the destination must be modifiable by the manager in the file manager.

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

Input Schema

NameRequiredDescriptionDefault
toNoSite folder to restore into, e.g. "assets/restored" (default: original location)
filesYesFile ids from amount.files, e.g. [12, 13]
overwriteNoReplace files that already exist. Default false.
delete_remoteNoDelete the remote copy after a verified download (destructive). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the single readOnlyHint=false annotation, the description discloses important behavior: background execution, return of a run uuid, original-location restoration versus `to` folder restoration, overwrite restrictions, refusal to write executables, and destination permission requirements. It omits any mention of the destructive `delete_remote` behavior described only in the 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 description is front-loaded with the core action and packs constraints efficiently without unnecessary preamble. It is somewhat dense and could be more scannable, but every clause carries operational information.

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?

For a background mutation tool with no output schema, the description explains the return value, destination behavior, overwrite policy, and key constraints. The main gap is that it does not mention the destructive remote-deletion option or how run status should be handled beyond referencing amount.status.

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?

With 100% schema coverage, the baseline is 3, but the description adds practical meaning for `files` by constraining ids to amount.files, max 200, and same-rule origin. It also clarifies `to` behavior and overwrite semantics beyond the schema, though it does not explain `delete_remote`.

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: bringing previously offloaded files back to the site. It scopes the input to ids from amount.files, at most 200, all from the same rule, making the operation clearly distinct from delivery or deletion siblings.

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?

It gives clear usage context: ids come from amount.files, must be capped at 200 per rule, and the operation runs in the background returning a uuid for amount.status. It does not explicitly state when to use another tool instead, but the intended workflow is evident.

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