SwitchWize MCP

Compare Accounts

compare_accounts

Read-onlyIdempotent

Compare two to five named banks on the editor-approved rates for savings, money market, checking or CDs (CDs by termMonths, default 12). For a balance, return each bank's APY, yearly interest, the gap to the best bank in your set and to the best verified rate, with verified date and source. Only banks in the approved set can be compared; a category with no current approved release returns data_unavailable and no rates. Illustrative interest before taxes, not a recommendation; verify eligibility and minimums.

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": {
      "category": "<category>",
      "accounts": "<accounts>"
    },
    "name": "compare_accounts"
  }
}

Input Schema

Name	Required	Description
`balance`	No	Dollars. Default 10000.
`accounts`	Yes	Two to five bank names or ids, e.g. ["Ally", "Capital One"].
`category`	Yes
`termMonths`	No	CDs only. Default 12.

Output Schema

Name	Required	Description
`asOf`	No	ISO timestamp of the underlying data this response reflects.
`note`	No
`tool`	Yes
`error`	No
`source`	No	Where the data comes from (URL).
`winner`	No
`balance`	No
`accounts`	No
`category`	No
`notFound`	No
`toolMeta`	No	Version and stability of the tool that produced this reply. See /developers#tool-versions.
`attribution`	No
`generatedAt`	Yes	ISO timestamp this response was computed at.
`verified_at`	No
`bestVerified`	No
`schemaVersion`	Yes
`methodologyUrl`	No
`freshnessStatus`	No
`comparison_status`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 2, 2026

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/openWorld, so the description focuses on adding real context: the verified date and source come back, missing categories degrade to data_unavailable with no rates, and figures are illustrative pre-tax and not a recommendation. It stops short of describing freshness/staleness behavior, which matters for a rate tool, but the fallback and disclaimer disclosure is substantive.

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?

Front-loads the comparison scope and the output content before the eligibility caveat, with no filler sentences. It is dense across four sentences but each carries distinct information; the disclaimer sentence is long but earns its place for a financial tool.

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?

Given four parameters, an output schema, and existing annotations, the description covers what is compared, what comes back, the failure mode for unapproved categories, and the illustrative/no-recommendation caveat. Nothing an agent needs to call it correctly or interpret the result is missing.

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 75%, and the description largely restates what the schema already documents ('CDs by termMonths, default 12', 'for a balance'). It does clarify that termMonths is CD-specific and that the comparison set is bounded to named banks, but adds little syntax or default detail beyond the schema fields.

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 (Compare) plus the exact resource and scope: two to five named banks, editor-approved rates, across four named categories. It is clearly separable from siblings like get_bank_gap (single bank gap), get_top_rates (list rankings) and compare_switch_savings (switching scenario), so an agent can route without opening the schema.

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?

Gives concrete use conditions: only banks in the approved set can be compared, and a category with no current approved release returns data_unavailable. It does not explicitly name when to prefer this over compare_switch_savings or get_bank_gap, so routing among the closest siblings is left to inference.

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

All SwitchWize MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.