Skip to main content
Glama

PointBagel

Application eligibility

application_eligibility
Read-only

The signed-in user's credit-card application posture, read from their own card history only: how many new cards they have opened in the last 24 months, which issuers they are at an application limit with, and counts of once-per-lifetime bonuses taken, cooldowns still running, and product conflicts in the way. It can also assess a specific card they name, including when a blocking rule clears, or a ranked shortlist of cards they could apply for next, drawn from their own spending; a card they already hold is reported as held, and a bonus at risk is flagged. Reflects the issuer eligibility rules PointBagel verifies; it never predicts approval odds and holds no credit-score, income, or SSN data. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "application_eligibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
candidateCardNo
includeApplyLinkNoOptional; this tool gives the same answer whether or not it is set. A link to apply comes only with a card PointBagel finds the user can apply for now, and only when PointBagel has one.

Output Schema

NameRequiredDescriptionDefault
asOfYes
dataYes
statusYes
summaryYes
nextActionsNo
userWarningsNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare read-only/non-destructive/closed-world, and the description reinforces this while adding real behavioral boundaries: it reflects only issuer rules PointBagel verifies, never predicts approval odds, and holds no credit-score, income, or SSN data. It also discloses edge-case handling (an already-held card reports as held, a bonus at risk is flagged, a blocking rule's clear date is surfaced), which an agent could not infer from annotations alone.

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 opening clause, and the long enumeration of reported signals is information-dense rather than padding. The single dense paragraph and stacked clauses make it slightly heavy to scan, but every sentence contributes a distinct fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, yet the description still characterizes the key outcomes and mode-dependent behavior. Combined with the explicit data-privacy and no-approval-prediction caveats, an agent has everything needed to choose and call it correctly with zero required parameters.

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

Parameters4/5

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

Schema coverage is 50%: includeApplyLink carries a description, but candidateCard has none. The description compensates by explaining that naming a card switches the tool into per-card assessment mode and by defining what a link means (only for a card the user can apply for now, and only when one exists). It stops short of format details such as whether a name or ID is expected.

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?

Names the specific resource (the signed-in user's credit-card application posture, drawn only from their own card history) and enumerates exactly what it reports: 24-month new-card count, issuer application limits, once-per-lifetime bonuses, cooldowns, and product conflicts. It further distinguishes its three modes (portfolio posture, named-card assessment, ranked shortlist), which separates it from portfolio-wide tools like portfolio_summary and card-specific lookups like card_detail.

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?

Usage is made concrete through mode cues: supply candidateCard to assess a named card, or omit it for a ranked shortlist of cards worth applying for next. It does not explicitly name a sibling or state when another tool would be preferable, so the routing guidance is contextual rather than explicit.

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