Skip to main content
Glama

adjust_rewards

Record reward balance adjustments that do not come from purchases, such as bonuses, redemptions, or expiries, with card, units, date, and note.

Instructions

Record points or cashback that did not come from a purchase.

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": {
      "card": "<card>",
      "units": "<units>",
      "note": "<note>"
    },
    "name": "adjust_rewards"
  }
}

Input Schema

NameRequiredDescriptionDefault
onNoYYYY-MM-DD, defaults to today
cardYesCard id, or its name (a unique part is enough)
noteYesWhat happened, e.g. 'Redeemed for Taj voucher'
unitsYesPositive to add (welcome bonus), negative to subtract (redemption, expiry)
value_inrNoRupee value received, if redeemed

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this mutates state in a non-destructive way. The description adds the useful distinction that these are non-purchase adjustments, but says nothing about effects on balance, reversibility, or whether negative units can drive a balance below zero.

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 front-loaded sentence with zero filler; the scoping constraint sits at the end where it reads naturally. Nothing is redundant or padded.

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 full parameter descriptions, the short description only needs to establish intent and scope, which it does. The minor gap is that behaviour on negative units and any interaction with existing balance is left entirely 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 description coverage is 100%, so the sign convention for units, the card-id-or-name resolution, the date default, and the rupee value are all already documented in the schema. The description adds no meaning beyond that, which is the expected baseline here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Record points or cashback that did not come from a purchase" gives a specific verb (Record) and resource (points/cashback) plus an exclusion that separates it from purchase logging. It stops short of naming the sibling that handles purchase-based rewards, so an agent must infer the pairing from the sibling list.

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?

The clause "did not come from a purchase" implicitly tells the agent when this applies, and the scope is clear enough to act on. It never explicitly states the alternative (log_purchase) or any prerequisites, so guidance is implied rather than stated.

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