Which of your cards to tap at a place: the cashback, cap and conditions, from the banks' own pages.
Scored across 1 tool
The server exposes a single tool with a tightly defined purpose: choosing the best card for a given place and card set. There are no overlapping tools, so an agent cannot misselect.
pick_card is a clear verb_noun name that accurately describes the action. With only one tool, there is no inconsistency to introduce.
A single tool fits the narrow card-selection purpose and avoids redundancy. However, the surface is minimal, with no auxiliary discovery or validation tools, so it is slightly thin.
The tool covers the core workflow end to end: it takes place and cards, ranks the best and second-best options, and returns caps, conditions, offers, and source links. Minor gaps remain, such as listing supported cards or places for discovery, but core usage is complete.
Use this when someone asks which of their credit or debit cards to pay with at a shop, app, category or city, to get the most cashback. Pass the place (a merchant such as Grab or Shopee, a category such as dining or supermarket, or a city such as Tokyo, or both: 'dining in Tokyo') and the cards they hold (names or ids). It answers in one line, 'use card X here, because Y, up to cap Z', with the second-best card, each card's cap and conditions, and the bank source link, plus the dated bank and card-network offers live at that place for those cards today. The data pack covers Vietnam-issued cards; amounts are in VND.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Purchase date YYYY-MM-DD. Default today in Vietnam. | |
| cards | Yes | The cards the person holds, by name ('VPBank Z JCB') or id ('vpbank-z-jcb'). | |
| picks | No | Bonus categories picked on pick-N cards, by group (vib-one, vib-max, cake-freedom, msb-mdigi). | |
| place | Yes | Merchant, category or city, for example 'Grab', 'supermarket', 'dining in Tokyo'. | |
| amount | No | Purchase amount, in VND unless currency says otherwise. Default 1,000,000 VND. | |
| channel | No | Online or in a shop, when the place alone does not say. | |
| currency | No | ISO code of amount when the person gives a foreign amount, such as JPY for 8,000 yen. The tool converts at its own dated rate; do not convert yourself. | |
| statement_spend | No | Spend so far this statement by card id, for minimum spend and tiers. |
| Name | Required | Description |
|---|---|---|
| best | No | |
| date | Yes | |
| pack | Yes | |
| check | Yes | |
| place | Yes | |
| amount | Yes | |
| answer | Yes | |
| offers | No | |
| second | No | |
| ranking | Yes | |
| currency | Yes | |
| freshness | No | |
| offers_total | No | |
| converted_from | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add what they cannot. It does: the one-line answer format ('use card X here, because Y, up to cap Z'), the second-best card, caps and conditions, bank source links, dated network offers, plus the data-scope limit (Vietnam-issued cards, VND amounts).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the trigger and input shape, then the output shape, then scope limits. It is dense but well ordered; a few clauses (e.g. repeating place forms and the VND note already in the schema) could be trimmed without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For an 8-parameter tool with nested objects, enums, and an output schema, the description supplies the missing pieces: the triggering scenario, the combined-place input pattern, the output contract in plain language, and the geographic/currency coverage boundary. Nothing an agent needs to call it correctly is absent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all 8 parameters are already documented, including place forms ('Grab', 'supermarket', 'dining in Tokyo'), card name/id formats, currency handling, and the VND default. The description largely restates these, so the baseline of 3 applies; the combined-place example ('dining in Tokyo') is the only semantic detail it reinforces.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: decide which held card to pay with at a given place to maximize cashback. It also names the concrete input dimensions (merchant, category, city, or a combination) and the answer shape, so an agent knows exactly what this tool produces.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Opens with an explicit trigger: 'Use this when someone asks which of their credit or debit cards to pay with at a shop, app, category or city.' There are no sibling tools and no stated when-not conditions, so there is nothing to route against, but the invocation context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
pick_card2 fields changedOutput schema / properties / offersAdded value: +{
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / offers_totalAdded value: +{
+ "type": "number"
+}pick_cardWhich of your credit cards to use at any store, from verified bank data. No bank login.
Which credit card earns the most at a merchant, from your cards or every card, and why.
Which card to use, what your points are worth, and whether each annual fee earns its keep.
Compare cashback rates from 100+ portals in 40+ countries and find discounted gift cards.
Add one secure layer between your agents and this server.
