Remote MCP server with health_check, pricing_list, money_fact, and scheme_lookup tools; prompts as on Smithery. Docs: https://bankrolled.ai/llms.txt
Scored across 4 tools
The four tools have mostly distinct roles: liveness check, single-fact retrieval, catalog listing, and deposit-insurance scheme lookup. money_fact and scheme_lookup are similar in shape (both return verified sourced data), but the descriptions clearly separate fact_keys from country-based scheme lookups, so misselection is unlikely.
All four names follow the same snake_case two-word noun_phrase pattern: health_check, money_fact, pricing_list, scheme_lookup. No camelCase mixing or divergent verb styles, so the pattern is fully predictable.
Four tools is a lean but defensible surface for a narrow read-only data/answer service: one health check, two data lookups, and one discovery/pricing tool. Nothing feels redundant, though the set is on the thin side and could support one or two more query tools (e.g. bulk or country-list retrieval).
For a read-only facts-and-coverage hub, the surface covers its core lifecycle: discovery (pricing_list), single-item retrieval (money_fact, scheme_lookup), and liveness (health_check). Minor gaps exist, such as no batch/multi-fact retrieval or enumeration of supported countries/fact_keys via a dedicated tool, but agents can work around these using pricing_list.
Check Agent Hub liveness (free). Returns ok, service, version, billed:false. No payment required.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description nonetheless adds value the annotations don't: it discloses the return payload shape (ok, service, version, billed:false) and confirms no payment/authorization is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two clipped sentences, with the core action (liveness check) front-loaded and the cost/return facts following. Every clause earns its place and there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter liveness probe with no output schema, the description supplies exactly what is missing: the call is free and the response fields are enumerated. Nothing an agent needs to call it correctly is absent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate; the schema is empty and 100% covered. Baseline of 4 applies for a no-parameter tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb and resource ("Check Agent Hub liveness") and even names the exact return fields, so an agent knows precisely what the tool does. It never names a sibling, but the "(free)" / "No payment required" framing implicitly separates it from the payment-oriented siblings like pricing_list and money_fact.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied rather than stated: it tells the agent this is a free liveness probe that needs no payment, which is a real selection signal against paid siblings. However, there is no explicit when-to-use, when-not-to-use, or named alternative, so the agent must infer the calling conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free. Fetch one verified money fact with official source and as-of date, plus source_url (bankrolled.com) and a cite line. Pass q = a fact_key or a short query. Supported fact_keys: us_fdic_standard_limit, us_fdic_joint_accounts, uk_fscs_deposit_limit, uk_fscs_temporary_high_balance, ca_cdic_deposit_limit, au_fcs_deposit_limit, nz_dcs_deposit_limit, uk_isa_annual_limit, us_401k_limit_2026, us_401k_catch_up_2026, us_roth_ira_limit_2026, ca_tfsa_limit_2026. Anything else → not_in_catalog (never invents). Full list with example queries: pricing_list.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | A fact_key (exact) or a short search query. fact_keys: us_fdic_standard_limit, us_fdic_joint_accounts, uk_fscs_deposit_limit, uk_fscs_temporary_high_balance, ca_cdic_deposit_limit, au_fcs_deposit_limit, nz_dcs_deposit_limit, uk_isa_annual_limit, us_401k_limit_2026, us_401k_catch_up_2026, us_roth_ira_limit_2026, ca_tfsa_limit_2026. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/openWorld, but the description adds real behavioral context: it is free, it never invents facts and returns not_in_catalog instead, and it always attaches an official source with an as-of date. That is meaningful disclosure beyond the structured fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core verb and return shape, and every clause carries information. The long fact_key enumeration duplicates the schema and costs some density, keeping it short of a 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, and the description compensates by describing the response fields (source, as-of date, source_url, cite line) and the failure mode. Enough for an agent to call it correctly, though exact response structure remains slightly implicit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the schema already documents q plus all twelve fact_keys and 24 examples. The description's 'q = a fact_key or a short query' restates the schema rather than adding syntax or format detail, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (Fetch) and resource (one verified money fact) plus the returned artifacts (official source, as-of date, source_url, cite line). It also names the sibling pricing_list, so an agent can distinguish it without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent what to pass (a fact_key or short query), enumerates the supported keys, defines the miss path (anything else → not_in_catalog), and routes to pricing_list for the full list of example queries. Both when-to-use and alternatives are covered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Agent Hub tools (all free) with example arguments and the full supported-queries list: every money_fact fact_key + example query and every scheme_lookup country. Docs https://bankrolled.ai/llms.txt.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true, idempotentHint=true and a closed world, so the safety profile needs no restating. The description adds that all tools are free and documents the return shape (examples plus supported-queries list), which is useful, but says nothing about size, rate limits, or freshness of the listing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence leading with the verb and resource, then specifics, then the docs URL. It is dense but every clause adds information; the only slight strain is the nested enumeration of fact_keys and countries.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema listing tool, the description covers what is returned (example arguments and the supported-queries list) and where to find more via the docs link. An agent would not be blocked by any missing detail, though return format specifics are only sketched.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly does not invent parameter behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb ("List") and resource ("Agent Hub tools") with a precise statement of what the listing contains: example arguments plus the full supported-queries set covering money_fact fact_keys and scheme_lookup countries. It is distinguishable from the siblings by tying its contents to them, though it never explicitly frames itself as the discovery entry point vs. those siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied rather than stated: the "full supported-queries list" wording signals this is the place to discover valid fact_keys and countries, and the docs link supports that. However, there is no explicit when-to-use or when-not-to-use instruction, and no guidance on how this relates to calling money_fact or scheme_lookup directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free. Look up the deposit-insurance scheme for an English-speaking country: name, coverage headline, official source, as_of, plus source_url (bankrolled.com) and a cite line. Supported countries: US, UK, CA, AU, NZ. topic: deposit_insurance (default). Example: country="CA".
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No | Topic key (default: deposit_insurance). | deposit_insurance |
| country | Yes | Country code: US, UK, CA, AU, or NZ. Example: "CA". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly, openWorld, idempotent), and the description adds useful context beyond them: that the call is free, the provenance domain (bankrolled.com), and an included cite line. It stops short of noting rate limits or freshness guarantees.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with cost and purpose, then scope, then parameters, with no filler. Densely packed but each clause (supported countries, default topic, example) earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description usefully enumerates the return fields (name, coverage headline, official source, as_of, source_url, cite line), which is exactly what an agent needs. Only minor gaps around error/unsupported-country behavior remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and both parameters already carry enums, defaults, and an example, so the description largely restates structured data. It adds only marginal framing and no syntax beyond what the schema shows.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (look up) and resource (deposit-insurance scheme), then enumerates the returned fields, making the tool's scope unambiguous. It is clearly distinct from siblings health_check, money_fact, and pricing_list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It names the supported countries (US, UK, CA, AU, NZ) and the default topic, which constrains when the tool applies, but never states when to prefer it over a sibling or what to do for an unsupported country. Usage is implied rather than guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
money_fact2 fields changedInput schema / properties / q / descriptionPrevious value: -"Short search query. Examples: \"fdic insurance limit\", \"uk isa annual limit\", \"tfsa contribution\", \"fscs deposit protection\"."New value: +"A fact_key (exact) or a short search query. fact_keys: us_fdic_standard_limit, us_fdic_joint_accounts, uk_fscs_deposit_limit, uk_fscs_temporary_high_balance, ca_cdic_deposit_limit, au_fcs_deposit_limit, nz_dcs_deposit_limit, uk_isa_annual_limit, us_401k_limit_2026, us_401k_catch_up_2026, us_roth_ira_limit_2026, ca_tfsa_limit_2026."Input schema / properties / q / examplesAdded value: +[
+ "us_fdic_standard_limit",
+ "us_fdic_joint_accounts",
+ "uk_fscs_deposit_limit",
+ "uk_fscs_temporary_high_balance",
+ "ca_cdic_deposit_limit",
+ "au_fcs_deposit_limit",
+ "nz_dcs_deposit_limit",
+ "uk_isa_annual_limit",
+ "us_401k_limit_2026",
+ "us_401k_catch_up_2026",
+ "us_roth_ira_limit_2026",
+ "ca_tfsa_limit_2026",
+ "fdic insurance limit",
+ "fdic coverage joint accounts",
+ "fscs deposit protection limit",
+ "fscs temporary high balance",
+ "cdic deposit insurance limit",
+ "australia fcs deposit guarantee",
+ "new zealand deposit compensation",
+ "isa annual contribution limit",
+ "401k contribution limit",
+ "401k catch up contribution",
+ "roth ira contribution limit",
+ "tfsa contribution limit"
+]scheme_lookup4 fields changedInput schema / properties / country / descriptionPrevious value: -"ISO-style country code: US, UK, CA, AU, or NZ. Example: \"CA\"."New value: +"Country code: US, UK, CA, AU, or NZ. Example: \"CA\"."Input schema / properties / country / enumAdded value: +[
+ "US",
+ "UK",
+ "CA",
+ "AU",
+ "NZ"
+]Input schema / properties / topic / descriptionPrevious value: -"Topic key (default: deposit_insurance). Example: \"deposit_insurance\"."New value: +"Topic key (default: deposit_insurance)."Input schema / properties / topic / enumAdded value: +[
+ "deposit_insurance"
+]health_checkmoney_factpricing_listscheme_lookup
Add one secure layer between your agents and this server.