Skip to main content
Glama

Preview a change

prepare_moneteka_action

Validate and preview one action on the signed-in person's account: a new purchase, a correction or removal of one purchase, wanting coins, no longer wanting a coin, a wanted coin that was bought, a message to MONETEKA support, or a change of a public link. Nothing changes and nothing is sent here. The result holds the preview for the user, an intent_id and commit_tool — the tool that applies this action once the user approves it.

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>"
    },
    "name": "prepare_moneteka_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesThe one change to preview. collection.add = a new purchase; collection.update = correct one purchase; collection.remove = delete one purchase; wishlist.add = want these coins; wishlist.remove = no longer want a coin; wishlist.acquire = a wanted coin was bought, move it into the collection; support.send = send a message to MONETEKA support; share.change = create, change, pause, replace or delete the public link of the collection or the wishlist.

Output Schema

NameRequiredDescriptionDefault
dataYes
as_ofYes
warningsYes
request_idYes
schema_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

The line 'Nothing changes and nothing is sent here' is high-value context that resolves the ambiguity created by readOnlyHint=false: the agent learns the tool stages rather than mutates. Remaining gaps are behavioral details such as whether a preview persists, how long an intent_id stays valid, and what happens on a revision conflict.

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-loads the preview-only purpose, then the no-side-effects guarantee, then the return contract. The action enumeration is long but each item maps to a distinct branch an agent must be able to recognize, so it earns its space; a small amount of tightening is possible.

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?

With annotations and an output schema already present, the description need only cover the safety profile and the commit handoff, which it does clearly. For a union-typed tool with eight action branches, the omission of intent_id lifetime and revision-conflict handling is a minor but real gap.

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

Parameters3/5

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

Schema description coverage is 100%, and the single 'action' parameter is already fully documented with a discriminator and a type-by-type mapping. The description's enumeration of action kinds largely restates that union, adding natural-language readability but no new constraints or semantics.

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 pair (validate and preview) on a specific resource (one action on the signed-in person's account) and enumerates the eight supported action kinds in plain language. It is clearly differentiated from the mutating siblings (add_collection_lot, update_collection_lot, send_support_message, manage_public_share) because it only stages the change.

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?

The description establishes the workflow position — preview here first, then apply via the returned commit_tool once the user approves — which is explicit when-to-use guidance. It stops short of naming sibling tools directly or stating exclusions, so the agent must infer from 'commit_tool' which sibling performs the write.

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