Skip to main content
Glama

SwitchWize MCP

Search Cards

search_cards
Read-onlyIdempotent

Search the credit cards SwitchWize lists (the same list as the /cards page) by issuer, network, goal, reward type, business or personal, maximum annual fee, welcome bonus and 0% intro APR. Each card returns confirmed fee, APR, rewards rate, welcome bonus, foreign transaction fee, verification state, last checked date and source URL. An unconfirmed term is null, never zero, and a filter on it leaves the card out. Not personalized advice.

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": "search_cards"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNo
sortNoDefault bonus.
limitNoDefault 20.
queryNoWords in the issuer or card name, e.g. sapphire.
issuerNoIssuer id or name, e.g. chase.
networkNo
businessNotrue for business cards only, false for personal cards only.
rewardModelNo
maxAnnualFeeNo
zeroIntroAprNo
hasWelcomeBonusNo

Output Schema

NameRequiredDescriptionDefault
asOfNoISO timestamp of the underlying data this response reflects.
noteNo
sortNo
toolYes
cardsNo
countNo
errorNo
sourceNoWhere the data comes from (URL).
toolMetaNoVersion and stability of the tool that produced this reply. See /developers#tool-versions.
attributionNo
generatedAtYesISO timestamp this response was computed at.
totalListedNo
verified_atNo
totalMatchedNo
schemaVersionYes
filtersAppliedNo
methodologyUrlNo
freshnessStatusNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds a genuinely non-obvious behavioral rule beyond them: unconfirmed terms are null (never zero) and filtering on such a term silently excludes the card, which materially changes how an agent should interpret and build filters. It also notes a verification state and last-checked date per card, though it stops short of pagination or result-size behavior.

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?

Three tight sentences: capability and filter surface first, per-card return fields second, the null-exclusion caveat third (the highest-value detail is preserved, not buried). No filler or restated field names; even the 'not personalized advice' line carries behavioral weight for framing output.

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, zero-required search tool with an output schema, the description covers scope, filters, and the null-handling rule that would otherwise cause wrong conclusions. Gaps are minor: no statement on result ordering/pagination beyond schema defaults and no pointer to the more targeted sibling tools for common lookups.

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 only 45% across 11 parameters, so the description must compensate, and it does: it names eight of the filters and frames maxAnnualFee as a ceiling and business as personal-vs-business exclusivity. The null/never-zero rule adds real semantic weight to filters like maxAnnualFee and hasWelcomeBonus where unknown values drop cards. It leaves query, sort, and limit to the schema, which already documents those three.

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?

States a specific verb (search) and resource (credit cards in the SwitchWize list) and enumerates the full filter surface: issuer, network, goal, reward type, business/personal, max annual fee, welcome bonus, 0% intro APR. The 'same list as the /cards page' scope note plus the breadth of filters implicitly distinguishes it from narrow siblings like cards_by_goal or best_card_for_spend.

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?

Usage is only implied: an agent can infer this is the general-purpose filtered lookup because of the broad filter list, but the description never says when to prefer it over cards_by_goal, compare_cards, or get_card_details, nor any when-not conditions. 'Not personalized advice' is a disclaimer, not usage guidance.

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.