Skip to main content
Glama

add_card

Add a credit card to the wallet with a preview and confirmation step, ensuring reward rates and statement dates are correct before saving.

Instructions

Add a credit card to the wallet, then call add_earn_rate for each category or merchant where it earns more than its base rate.

Wrong terms silently skew every later recommendation, so saving needs the user's
agreement: call once without `confirmed` to get a preview, show it to the user
(including anything found with search_card_terms and their statement day), and
call again with confirmed=true only after they agree.

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": {
      "name": "<name>",
      "issuer": "<issuer>",
      "reward_kind": "<reward_kind>",
      "base_rate": "<base_rate>"
    },
    "name": "add_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesCard name as the user calls it, e.g. 'HDFC Millennia'
notesNoFees, perks, anything worth remembering
issuerYesIssuing bank
networkNoVisa, Mastercard, RuPay, Amex, Diners
base_rateYesUnits earned per block_inr on regular spends. 1% cashback = 1 with block_inr 100; '4 points per ₹150' = 4.
block_inrNoSpend (₹) that earns base_rate units, e.g. 150
confirmedNoSet true only after the user has seen and agreed to these terms. Without it the card is previewed, not saved.
reward_kindYes
statement_dayNoDay of the month the billing cycle starts
unit_value_inrNoRupee value of one point. Required for points cards; cashback defaults to 1.
excluded_categoriesNoCategories that earn nothing on this card. Defaults to fuel, government, rent, wallet

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes well beyond that by disclosing the dry-run/preview semantics of an unconfirmed call, the downstream consequence ("wrong terms silently skew every later recommendation"), and the human-approval requirement. It does not cover edge behavior such as what happens when a duplicate card already exists or validation failures, so it stops short of fully transparent.

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 is front-loaded in the first clause, and the second paragraph carries the confirmation protocol with no filler. The final sentence is long and packs several instructions together, which slightly reduces scannability but the content all earns its place.

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?

For an 11-parameter mutation tool with real downstream effects, the description covers the risky behavior (preview vs save), the approval gate, and the chained follow-up tool; an output schema exists so return values need no explanation. Remaining gaps are duplicate-card handling and the points-card requirement for unit_value_inr, which are left to the schema.

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 coverage is 91% and the schema already explains `confirmed` ("Without it the card is previewed, not saved") and `statement_day`. The description mostly restates that in workflow terms rather than adding new per-parameter meaning, so the baseline 3 applies.

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?

"Add a credit card to the wallet" is a specific verb+resource, and the same sentence names the required follow-up (add_earn_rate per category/merchant above base rate). An agent can immediately distinguish this from add_earn_rate, update_card, or card_details 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?

The description gives an explicit two-phase calling protocol: call once without `confirmed` to preview, show the user the terms (including search_card_terms results and the statement day), then call again with confirmed=true. It also names the sibling to invoke afterward, so both when-to-use and what-to-do-next are covered.

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