Skip to main content
Glama

PointBagel

How adding a card would change your rewards

card_impact
Read-only

Estimate how adding a candidate card would change the signed-in user's annual rewards: the ongoing per-year value change from earning alone (extra earn minus extra fees), the same change with the card's recurring credits and perks added at PointBagel's catalog estimate, the published statement-credit maximums behind that estimate, which spending categories would move to the new card, the wallet's total annual earn before and after, and the one-time welcome offer kept separate from the recurring math. Modeled against the user's own tracked spending over the last 12 months. Values are estimates, never approval predictions. annualFee is priced for this reader; see annualFeeNote.

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>"
    },
    "name": "card_impact"
  }
}

Input Schema

NameRequiredDescriptionDefault
cardYes
styleNo
includeApplyLinkNoSet to true when the user is deciding whether to apply for this card. The answer then includes PointBagel's apply link and its disclosure when PointBagel has one for this card.

Output Schema

NameRequiredDescriptionDefault
asOfYes
dataYes
statusYes
summaryYes
nextActionsNo
userWarningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the read-only and non-destructive annotations, it discloses the 12-month personal-spending baseline, the treatment of recurring earnings, fees, catalog-valued perks, statement-credit caps, and the separation of one-time welcome offers. It also warns that results are estimates rather than approval predictions and that annualFee is reader-specific with an accompanying note.

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?

The description is front-loaded, and every sentence contributes methodology, scope, or an interpretation caveat without promotional filler. Its first sentence is an overloaded output inventory, however, and some of that detail could be left to the existing output schema to make room for input guidance.

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?

Together with the output schema and safety annotations, this gives an agent substantial context about the model, its data basis, and important interpretation caveats. It falls short of full completeness because the required card input's accepted form and the optional style's effect are unspecified, and there is no explicit sibling routing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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

Only includeApplyLink is documented in the schema, and the description does little to close the remaining gap: 'candidate card' gives card a general meaning but no accepted identifier or name format, while style's conservative, balanced, and aspirational choices are never explained. The annualFee and annualFeeNote sentence concerns output pricing rather than helping an agent choose an input.

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?

The opening verb and scope are precise: estimate a candidate card's effect on the signed-in user's annual rewards, including before-and-after wallet earn and category shifts. This is much more informative than the title, but it never names or explicitly differentiates a sibling, so sibling-level disambiguation is incomplete.

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

Usage Guidelines4/5

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

It establishes a clear what-if evaluation for a particular candidate using the user's tracked spending, and explicitly says the values are estimates rather than approval predictions. The includeApplyLink schema also supplies a concrete decision-to-apply trigger, but no alternative tool is named for approval, selection, or other adjacent needs.

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