Skip to main content
Glama

PointBagel

Best redemption path

best_redemption
Read-only

For ONE of the signed-in user's points programs: the estimated value of their balance and the valuation basis behind it, the program type, its transfer partners with current ratios and whether PointBagel has verified a route out, published transfer times, the sweet-spot awards worth aiming for, the kind of price each carries, how far the balance goes toward each, where to confirm each award (plain links), any transfer-bonus cap in the issuer's units, and which card would unlock full transfer access. Point values are estimates, not promises. Does NOT check live award availability; for open award seats use point.me, Seats.aero, or the airline. Read-only; the user's own balances only.

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": {
      "program": "<program>"
    },
    "name": "best_redemption"
  }
}

Input Schema

NameRequiredDescriptionDefault
filtersNoOptional filters that narrow PointBagel's catalogued award sweet spots: destination region, cabin, trip type, and the most points the user wants to spend on one award, in this program's own points. round_trip keeps one-way awards, since a round trip is two of them; one_way leaves out awards priced as a round trip. An award whose price can run above the points cap is left out. They do not check whether award seats or rooms are available.
programYesA points program name or id, e.g. "Chase Ultimate Rewards" or "amex_mr".

Output Schema

NameRequiredDescriptionDefault
asOfYes
dataYes
statusYes
summaryYes
nextActionsNo
userWarningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds genuinely new behavioral context by warning 'Point values are estimates, not promises' and stating the data is limited to the signed-in user's own balances. It also discloses that transfer-bonus caps are expressed in the issuer's units, which affects interpretation. It does not mention latency, catalog freshness, or failure behavior for an unknown program.

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

Conciseness3/5

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

Scope is front-loaded correctly and the caveat sentences earn their place, but the bulk of the text is a long run-on enumeration of ten-plus returned fields even though an output schema exists. That inventory is largely redundant and should be compressed so the caveats and boundaries stand out.

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 a read-only, single-required-parameter lookup with an output schema, the definition supplies the essential trust caveats (estimates not promises, no live availability, own balances only). The remaining gap is that it never explains the optional filters' effect on results, which an agent would otherwise assume from the schema alone.

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 100%, with a rich nested description of the filters object already explaining cabin, region, trip type, maxSourcePoints and the round_trip/one_way semantics, so the baseline is 3. The description adds nothing about how filters narrow the sweet-spot list or what happens when a program name is ambiguous, so it neither compensates nor detracts.

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 description makes the resource and scope explicit: 'For ONE of the signed-in user's points programs' with estimated balance value, valuation basis, transfer partners, sweet spots and unlock cards. The action is conveyed as a list of returned content rather than a stated verb, and no sibling tool (e.g. transfer_bonuses, card_impact, which_card) is named for contrast, so differentiation is inferred rather than stated.

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 draws a clear boundary: 'Does NOT check live award availability; for open award seats use point.me, Seats.aero, or the airline,' and restricts scope to 'the user's own balances only.' The alternatives offered are external services rather than sibling tools, so an agent gets a use/don't-use line but no in-server routing to transfer_bonuses or card_detail.

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