Skip to main content
Glama

PointBagel

Which card to use, from cards you name

which_card_for_named_cards
Read-only

Recommend which credit card to use for a store or spending category from the cards the user names in the conversation, including cards they have not saved to PointBagel yet. Each named card is priced from PointBagel's verified catalog: the earn rate, the estimated value per dollar, and the runner-up cards. Spending caps are treated as unspent, and a rotating quarterly bonus that needs activation counts only for a card the user says they activated this quarter. Asks which card was meant when a name matches more than one, marks cards already saved to this account, and says how to save the rest. For cards already saved, which_card answers from the user's own spending and caps instead. Values are estimates. Read-only.

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": {
      "query": "<query>",
      "cards": "<cards>"
    },
    "name": "which_card_for_named_cards"
  }
}

Input Schema

NameRequiredDescriptionDefault
cardsYesThe credit cards the user named, as they said them, e.g. "Sapphire Preferred".
queryYesA store or spending category, e.g. "Costco", "dining", or "gas".
styleNoRedemption style for valuing points. Defaults to the user's saved style, else "balanced".
amountNoPurchase amount in US dollars. Defaults to a small purchase.
portalNoThe name of the travel portal the user says they are booking through, such as "Chase Travel", with bookingChannel set to portal.
bookingChannelNoHow the user says they are booking this purchase: direct with the supplier, through a portal (name it in portal), or other for any other way, such as an online travel agency. Put only the purchase in query. Leave this unset when the user has not said, has only said what they are not using, or is unsure; never assume it.
activatedThisQuarterNoOnly when the user said so: the named cards whose rotating quarterly bonus they activated this quarter, spelled as in cards.

Output Schema

NameRequiredDescriptionDefault
asOfYes
dataYes
statusYes
summaryYes
nextActionsNo
userWarningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds real substance beyond that: spending caps are assumed unspent, a rotating quarterly bonus counts only if the user says it was activated, values are estimates, and ambiguous names trigger a clarifying question. The trailing 'Read-only.' merely restates the annotation, but the rest is substantive.

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?

Purpose and scope are front-loaded in the first sentence, followed by pricing semantics, edge-case handling, and sibling routing, so the structure is easy to scan. It is dense but nearly every sentence carries new information, with only the final 'Read-only.' being redundant against the annotations.

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?

An output schema exists, so return values need not be described. For a 7-parameter read-only recommendation tool, the description covers the pricing assumptions, activation handling, ambiguity resolution, and the sibling split with which_card — nothing an agent needs 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 the baseline is 3. The description goes beyond the schema by explaining the pricing model behind activation and caps ('spending caps are treated as unspent', 'a rotating quarterly bonus that needs activation counts only for a card the user says they activated this quarter'), which tells the agent what activatedThisQuarter actually changes in the result. The 'values are estimates' note also frames the style parameter's effect.

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 opening sentence states a specific verb (recommend), resource (credit card), and scope (a store or spending category, restricted to cards the user named in conversation, including unsaved ones). It also explicitly carves out the sibling case: saved cards go to which_card. An agent can distinguish it from which_card and add_cards_* without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit routing rule: use this for cards the user names (even unsaved), use which_card when the cards are already saved, because that tool answers from the user's own spending and caps. It also states the disambiguation behavior when a name matches multiple cards, covering the main ambiguity an agent will hit.

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