Query Bancadia's registry of US business checking account products with structured filters.
Scored across 2 tools
The two tools occupy clearly separate roles: query_business_checking performs broad filtered list searches, while get_business_checking_listing retrieves full detail for a single listing identified by listing_slug. The descriptions explicitly frame the get as a follow-up to the query, so an agent cannot reasonably confuse them.
Both names are snake_case and domain-anchored (business_checking), giving a readable, predictable family. The verb choice is slightly inconsistent, though: 'query_' for the list operation versus 'get_' for the detail operation, and one name embeds the resource noun while the other does not.
Two tools is thin even for a read-only registry service, though the list-plus-detail pair does cover the core lookup workflow. A comparison or filter-discovery operation would round it out; as-is it sits at the borderline-minimal end.
Core read workflow (search listings, then drill into one) is present with no dead end for the primary use case. However, there is no way to enumerate available filter values, look up an institution independently, or compare multiple listings, which limits deeper research tasks.
Get full detail on one specific business checking listing, including gotcha fees (business_deposit_fees, e.g. overdraft, NSF, dormancy) and feature narrative (business_deposit_account_features) not returned by query_business_checking's broad list results. Fees/features that apply to only one plan tier (e.g. a Standard/Plus/Premier ladder) are nested under that tier in plan_tiers[].fees / plan_tiers[].features; tier-agnostic ones are in the top-level general_fees / general_features. Use this as a follow-up after query_business_checking to dig deeper on one listing the caller already identified by its listing_slug. Each result's application_url is a tracked Bancadia link: give it to the user exactly as returned, including its query string.
| Name | Required | Description | Default |
|---|---|---|---|
| listing_slug | Yes | The listing's stable public identifier, as returned in query_business_checking results (e.g. 'found-business-checking'). Do not use an internal database id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden and does well: it discloses the returned data shape (tier-nested vs tier-agnostic fees/features) and a real behavioral constraint that application_url is a tracked Bancadia link to be passed through verbatim with its query string. It does not state read-only/no-side-effect behavior or auth requirements, which is the remaining gap.
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 action, then layers detail field-by-field; every sentence carries operational information. It is dense with internal field names (plan_tiers[].fees) but none of it is filler, so the length is earned though slightly heavy.
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 must explain the return shape and it does, including the tier-nesting rule and the tracked-link caveat. For a single-parameter lookup tool this covers everything an agent needs to call it correctly and hand results to a user.
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 the schema itself already warns against internal database ids. The description adds pipeline provenance beyond the schema by tying listing_slug to values previously returned by query_business_checking, which helps the agent source the value correctly.
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 and resource ('Get full detail on one specific business checking listing') and explicitly contrasts its depth with the sibling's 'broad list results'. An agent can distinguish it from query_business_checking without opening either 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 prescribes the workflow: 'Use this as a follow-up after query_business_checking to dig deeper on one listing the caller already identified by its listing_slug.' The alternative (broad list) and the condition selecting this tool are both named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query the Bancadia registry for business checking account products using compound filter criteria. Returns active, verified listings from financial institutions. Optionally accepts target_industries/target_business_profiles to soft-rank results toward listings built for a given business type or stage — non-matching but eligible listings are still returned, just ranked lower. Each result's application_url is a tracked Bancadia link: give it to the user exactly as returned, including its query string.
| Name | Required | Description | Default |
|---|---|---|---|
| apy_min | No | Only return accounts whose best available rate (apy_max) is at least this value, as a decimal (e.g. 0.02 = 2%). This is the best rate the account can pay, not what a typical customer gets — many accounts pay less by default. Check apy_default in the results for the standard rate. | |
| rtp_network | No | Which real-time payment rail is supported | |
| rtp_supported | No | Whether real-time payments (any rail) are supported at all | |
| insurance_type | No | Deposit insurance type | |
| monthly_fee_max | No | Maximum monthly fee | |
| available_states | No | Returns listings available in all specified states | |
| interest_bearing | No | Whether the account earns interest | |
| target_industries | No | Soft-ranks results toward listings built for these business types. Does not exclude non-matching but otherwise-eligible listings. | |
| entity_types_accepted | No | Returns listings accepting all specified entity types (e.g. llc, s_corp) | |
| free_transactions_min | No | Minimum free transactions per month | |
| cash_deposit_available | No | Whether cash deposits are supported | |
| sub_accounts_supported | No | Whether sub-accounts are supported | |
| target_business_profiles | No | Soft-ranks results toward listings built for this business stage/shape. Does not exclude non-matching but otherwise-eligible listings. | |
| tax_integration_available | No | Whether the account connects to any tax-prep or tax-filing software/service | |
| minimum_opening_deposit_max | No | Maximum minimum opening deposit | |
| expense_integration_available | No | Whether the account connects to any expense/spend-management software | |
| accounting_integration_available | No | Whether the account connects to any accounting software (e.g. QuickBooks, Xero) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does notable work: it discloses that only 'active, verified' listings are returned, that target_industries/target_business_profiles only re-rank and never exclude eligible listings, and that application_url is a tracked link that must be passed through verbatim with its query string. It omits pagination, result caps, and any auth/rate-limit behavior, so it falls short of full coverage.
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?
Four sentences, front-loaded with purpose, then return semantics, then soft-rank caveat, then the link-handling instruction. Nothing is padded, though the soft-rank point is made twice (in the description and again in the two param descriptions), a mild redundancy.
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 17-param query tool with no output schema and no annotations, the description covers the essentials an agent needs: what it searches, that results are active/verified, that target_* params are ranking-only, and how to handle the tracked URL. Missing pagination/result-count behavior is the main gap, but the parameter schema is exhaustive.
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% across 17 params, including the enum meanings and the apy_min/apy_max distinction, so the schema already does the heavy lifting. The description restates the soft-rank semantics of the two target_* params but adds no format or syntax detail beyond what the schema provides. 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 and resource: 'Query the Bancadia registry for business checking account products using compound filter criteria.' It is unambiguous about what the tool returns (active, verified listings), but it never names or contrasts with the sibling get_business_checking_listing, so the agent must infer that this is the search/browse tool and the sibling is the single-record fetch.
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 by the filter-oriented phrasing and the explicit soft-rank behavior, but there is no statement of when to prefer this over get_business_checking_listing or when not to use it. The soft-rank explanation does usefully tell the agent not to expect hard exclusion from those two params, which is a form of guidance, but routing between 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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
query_business_checking1 field changedInput schema / properties / apy_min / descriptionPrevious value: -"Minimum APY (inclusive), for interest-bearing accounts"New value: +"Only return accounts whose best available rate (apy_max) is at least this value, as a decimal (e.g. 0.02 = 2%). This is the best rate the account can pay, not what a typical customer gets — many accounts pay less by default. Check apy_default in the results for the standard rate."get_business_checking_listingquery_business_checkingCitable US facts w/ curated query templates: SEC financials, bank call reports, nonprofits. No key.
Bank account terms as banks publish them, dated: fees, waivers, offers. Read-only. Canada today.
US business location data: search, sample, count, query rows or buy CSVs (Stripe or x402 USDC).
U.S. business-registry data and change events from official state sources, for agents.
Add one secure layer between your agents and this server.