Is this bank FDIC-insured, healthy and open? Bank profiles, ROA/ROE and failures from FDIC.
Scored across 4 tools
Each tool has a clearly distinct role: name-based lookup, failure history, cert-number profile, and state-level screening. There is little risk of confusing them, even though bank_check and bank_profile both return institution details.
All names are snake_case, but the pattern is mixed: three use a bank_ prefix while one uses state_screen, and the names are noun-like descriptors rather than a consistent verb_noun convention. They remain readable and understandable.
Four tools are well-scoped for a focused FDIC bank data server: a free lookup, failures list, detailed profile, and state screen. Each tool earns its place without excessive breadth.
The surface covers the core workflows: checking a bank, viewing failures, retrieving a full profile by cert, and screening banks by state. Minor gaps exist, such as national asset-ranked searches or richer branch/deposit-market-share queries, but agents can work around them.
FREE. Is this US bank FDIC-insured and active? Name search → top 3 with assets, deposits and location.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose useful traits: it is free, it is a lookup (non-mutating by nature), and it returns a bounded top 3 with specific fields — which partially substitutes for the missing output schema. It does not say whether data is live, how matches are ranked, or what happens when no name matches.
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 short, front-loaded sentences: the cost hook ('FREE') and the core question lead, then the result shape. The arrow shorthand is slightly cryptic but still parses in one read.
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 one-parameter lookup with no annotations and no output schema, the description covers the return shape well, which is the main gap it needed to close. It falls short on name formatting and on routing versus bank_profile, both of which an agent needs before choosing this tool.
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 single 'name' parameter has 0% schema description coverage, so the description must compensate. 'Name search' usefully implies the parameter is the bank's name rather than an ID, but it gives no guidance on format — legal name vs. partial string, abbreviations, or how broad matches are matched.
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 question it answers (is this US bank FDIC-insured and active) and the mechanism (name search returning top 3 with assets, deposits, location). This is clear enough to act on, but it never distinguishes itself from the sibling bank_profile, which plausibly answers overlapping questions.
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?
No when-to-use or when-not-to-use guidance, and no mention of the sibling bank_profile that likely competes for the same lookup intent. Only an implicit cue ('Name search') suggests you need a bank name to call it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Recent US bank failures (and acquirers), newest first, optional state filter.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | ||
| since_year | No | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It usefully discloses ordering (newest first) and geographic scope (US), but omits what 'recent' means (time window), whether results are paginated or capped, and the subscriber-auth requirement — the 'PRO' prefix hints at it but never states it.
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?
One compact sentence with the resource and ordering front-loaded; nothing is wasted. The cryptic 'PRO.' prefix is the only slightly unclear element.
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 3-parameter tool with no annotations and no output schema, the description leaves too much open: since_year semantics, the definition of 'recent', the auth/token requirement, and any result limits are all unaddressed.
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 only 33%. The description clarifies that state is an optional filter, but says nothing about since_year, which is entirely undocumented in both schema and description, so the agent cannot tell what it constrains.
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 resource (recent US bank failures and acquirers), an ordering (newest first), and a scope modifier (optional state filter). It is clearly distinct from siblings like bank_check and bank_profile, though it never names them explicitly.
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?
No guidance on when to use this versus bank_check, bank_profile, or state_screen, and no prerequisites mentioned. The only usage signal is the implied 'use this to list failures' from the title-like phrasing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Full profile for an FDIC cert number: assets, deposits, ROA/ROE, offices, regulator, holding company.
| Name | Required | Description | Default |
|---|---|---|---|
| cert | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden; it does disclose the returned data categories, which is genuinely useful since there is no output schema. However, it says nothing about authentication requirements (the 'PRO' tier and access_token imply a subscription gate), rate limits, or what happens on an invalid/unknown cert.
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 compact sentence with the key input and the output payloads front-loaded; nothing is wasted or repeated from the schema.
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 two-parameter lookup with no output schema, listing the returned fields makes the definition largely self-sufficient. The remaining gap is the unexplained 'PRO' tiering and auth expectations, which the schema's access_token description only partly covers.
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 50%; access_token is documented in the schema as a subscriber token, while cert has no schema description. The description partially compensates by clarifying that cert is an FDIC certificate number rather than a name or ticker, which is the key semantic needed to call the tool 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?
The description names a concrete lookup key (FDIC cert number) and enumerates the returned fields (assets, deposits, ROA/ROE, offices, regulator, holding company), so the agent knows exactly what this retrieves. It does not explicitly contrast itself with bank_check, though the word 'Full' implies broader coverage than a mere check.
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 only implied: the 'Full profile' phrasing hints that this is the comprehensive option versus bank_check, and 'PRO.' hints at a paid/subscriber tier, but neither is stated as a condition for use. No sibling is named and no when-not-to-use guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Active banks in a state ranked by assets or weakest ROA — for B2B sales, vendors and counterparty screens.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | assets (default) | weakest_roa | |
| limit | No | ||
| state | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that results are limited to active banks, can be ranked by assets or weakest ROA, and that the tool is PRO-gated, but it does not explicitly confirm read-only behavior, describe limit/pagination behavior, or detail authentication requirements beyond the schema.
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?
The description is a single compact sentence plus a PRO marker, with the core purpose front-loaded and no wasted text. It is appropriately sized for a simple screening tool.
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 four-parameter, no-output-schema, no-annotation tool, the description covers purpose, scope, ranking modes, and use cases. However, it leaves gaps around the limit parameter, auth expectations, and return shape that would help an agent invoke it confidently.
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 50%, with descriptions for sort and access_token but not state or limit. The description adds meaning for state scoping and the two ranking modes, but it does not explain the limit parameter or access_token requirements beyond the word PRO.
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 clearly states the resource and scope: active banks in a state, ranked by assets or weakest ROA. It does not explicitly differentiate from siblings like bank_check or bank_profile, but the screening purpose is unambiguous.
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 gives clear intended use cases: B2B sales, vendors, and counterparty screens. It does not mention when not to use it or name sibling alternatives, but the context is sufficient for selection.
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.
bank_checkbank_failuresbank_profilestate_screenBank financials, branch locations, deposit data, and failure history from FDIC
Search FDIC-insured banks, Call Report financials, peer rankings, failures, mergers, deposit share.
FDIC MCP — FDIC BankFind Suite API (free, no auth)
Community bank intelligence: FDIC financials, peer benchmarking, HMDA lending and CRA posture.
Add one secure layer between your agents and this server.
