Skip to main content
Glama

PointBagel

Save cards to your wallet

add_cards_confirm
DestructiveIdempotent

Save the cards from an add_cards_preview answer to the user's PointBagel wallet, after the user agrees to that list. Pass the save code and the card names exactly as add_cards_preview listed them. Saves only the catalog card and, when the user stated it, the month it was opened: never a nickname, a card number, or anything the user said. A save code works once and expires ten minutes after the preview. Never changes or removes a card already in the wallet. PointBagel then sends the user an in-app notice and, when it can, an email listing the cards saved; the answer says which were sent.

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": {
      "saveCode": "<saveCode>",
      "cardNames": "<cardNames>"
    },
    "name": "add_cards_confirm"
  }
}

Input Schema

NameRequiredDescriptionDefault
saveCodeYesThe saveCode from the add_cards_preview answer.
cardNamesYesThe card names exactly as add_cards_preview listed them in confirmCardNames.

Output Schema

NameRequiredDescriptionDefault
asOfYes
dataYes
statusYes
summaryYes
nextActionsNo
userWarningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

The description adds substantial behavioral context beyond the annotations: the save code works once and expires ten minutes after the preview; the tool persists only the catalog card and, if the user stated it, the opened month, never a nickname, card number, or anything else the user said; it never alters or removes an existing wallet card; and it triggers an in-app notice, plus an email when possible. That is meaningful disclosure. There is, however, mild tension with the structured hints: the annotations set idempotentHint=true, yet the one-time, ten-minute expiry code means a repeat call cannot succeed, and destructiveHint=true sits oddly against the claim that existing wallet cards are never changed or removed. The description clarifies scope rather than directly contradicting the annotations, but it does not address the retry/idempotency behavior.

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 action statement, followed by the constraints and side effects in a logical order. Every sentence carries a distinct rule (data minimization, code expiry, no mutation of existing cards, notifications), and little is padded, though the notification sentence is the least essential.

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 two-parameter write tool with a full schema and an output schema, this description covers the prerequisites, the payload fidelity, the code lifetime, the persisted fields, the non-effects on existing cards, and the notification side effects; it defers return-shape detail to the output schema. Nothing an agent needs in order 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.

Parameters4/5

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

Schema coverage is 100%, so both parameters are already documented, which sets the baseline at 3. The description adds real meaning for saveCode, however: it says how long the code is valid and that it can be used only once, which the schema does not say. It also warns that the card names must be passed exactly as they were listed, reinforcing the schema wording.

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 names a specific verb and resource: it saves the cards from an add_cards_preview answer to the PointBagel wallet, and only after the user has agreed to that list. That wording tells the agent this tool is the confirm/save step, whereas add_cards_preview is the preview step, so the agent can tell the sibling tools apart.

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 states the prerequisite clearly: it is called after the user agrees to the list, and with the saveCode and the names exactly as add_cards_preview returned them. It does not spell out a failure path for a user who rejects the list or for an agent that has never called the preview, so it falls short of a full when/when-not guide.

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