Skip to main content
Glama

recommend_card

Read-only

Ranks every card in the wallet by the rupee value of rewards it returns on a purchase, factoring in earn rates and monthly caps already used. Input amount and merchant to find the best card to pay with.

Instructions

Rank every card in the wallet by the rupee value it would give back on this purchase, taking monthly caps already used into account.

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": {
      "amount": "<amount>",
      "merchant": "<merchant>"
    },
    "name": "recommend_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountYesPurchase amount in ₹
channelNooffline
categoryNoSpending category, see the smartcard://categories resource. Leave empty to guess from a well-known merchant.
merchantYesWhere the user is buying, e.g. 'Amazon'

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

readOnlyHint=true already declares the safety profile, so the description's job is to add behavioral nuance, and it does: it discloses that the ranking is value-based in rupees and that already-consumed monthly caps are taken into account. It also implies a full ranked list rather than a single winner. It stops short of describing tie-breaking or how cards with no applicable earn rate are handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the action and ranking basis front-loaded and no filler. Every clause (wallet-wide, rupee value, cap awareness) carries distinct 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?

With an output schema present and readOnlyHint set, the description only needs to establish purpose and the ranking basis, which it does. Minor gaps remain around edge cases such as an empty wallet or cards with exhausted caps, but 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.

Parameters3/5

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

Schema description coverage is 75%, so the schema already carries most parameter meaning — amount, merchant, channel enum, and category (including a pointer to the smartcard://categories resource). The description adds only that these inputs define "this purchase"; it gives no additional guidance on parameters, which is the expected baseline when the schema does the work.

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 uses a specific verb ("rank") on a specific resource ("every card in the wallet") for a specific input ("this purchase"), and adds the non-obvious qualifier that monthly caps already consumed are factored in. That distinguishes it cleanly from siblings like list_cards, rewards_balance, or spending_report.

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

Usage Guidelines3/5

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

Intended use is implied — pick the best card to pay with for a given purchase — but there is no explicit when-to-use/when-not framing or reference to a related tool such as rewards_balance for general reward inspection. An agent can infer the context but isn't told any preconditions (e.g. that the wallet must already contain cards).

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