Bank financials, branch locations, deposit data, and failure history from FDIC
Scored across 5 tools
Each tool has a distinct target: failures, county branches, institution detail, institution branches, and institution search. The two branch tools (get_county_branches vs get_institution_branches) share a subject and could momentarily be confused, but the description scoping by geography vs institution disambiguates them.
All tools use snake_case with a consistent verb_noun pattern (get_bank_failures, get_county_branches, get_institution, get_institution_branches, search_institutions). The single search_ verb alongside get_ is idiomatic and still fully predictable.
Five tools is lean but reasonable for a read-only data API focused on institution lookup, branch data, and failures. It covers the main FDIC access patterns without bloat, though it is on the thin side for a full data domain.
Core read workflows are covered: search, institution detail, branch data by institution and county, and failure history. Gaps exist around historical/financial time-series and location-based searches, but for a read-only reference API the surface is largely complete with no dead ends.
Get recent bank failures from FDIC records.
Returns details of failed FDIC-insured institutions including failure
date, resolution type, estimated cost, and pre-failure assets.
Args:
state: Two-letter state abbreviation to filter by (e.g. 'CA').
start_year: Only return failures from this year onward (e.g. 2020).
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | ||
| start_year | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It lists returned fields but fails to disclose behavioral traits like read-only nature, rate limits, authentication needs, or data freshness. A basic query tool with limited transparency.
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 concise at ~3 sentences plus parameter docs, front-loaded with purpose. Lacks slight efficiency but no verbosity.
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 output schema present and 2 optional parameters, the description covers core functionality. Missing details on default behavior when no parameters given, but sufficient for basic use.
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 0%, so the description must compensate. It adds useful context: 'state' as two-letter abbreviation, 'start_year' as year onward. This goes beyond raw types, though more format details could help.
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 'Get recent bank failures from FDIC records' with a specific verb and resource, and it distinguishes from sibling tools focused on branches and institutions.
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?
The description implies usage through parameters but provides no explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all bank branches in a county ranked by deposits.
Returns branch-level deposit data from the Summary of Deposits (SOD)
for all institutions in the specified county.
Args:
state_fips: Two-digit state FIPS code (e.g. '06' for California).
county_fips: Three-digit county FIPS code (e.g. '037' for Los Angeles).
| Name | Required | Description | Default |
|---|---|---|---|
| state_fips | Yes | ||
| county_fips | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. It mentions the output is ranked by deposits and sourced from SOD, but does not disclose data freshness, pagination, or completeness. Provides adequate transparency for a read operation.
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?
Concise two-paragraph description with clear function and args section. No unnecessary words, front-loads main purpose.
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?
Provides essential info for a simple lookup tool. Output schema exists but return details are not in description; mentions ranking but not order. Still fairly complete given tool complexity.
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?
With 0% schema description coverage, the description fully explains both parameters: state_fips and county_fips, including FIPS format and examples. This adds significant value beyond the schema.
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 tool gets all bank branches in a county ranked by deposits, specifying the data source (Summary of Deposits). This distinguishes it from siblings like get_institution_branches (likely for a specific institution) and search_institutions.
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 tool versus alternatives like get_institution_branches or search_institutions. The description only provides input parameters without usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed financial information for a specific FDIC-insured institution.
Returns Call Report data for the most recent reporting period (2024-06-30)
including assets, deposits, income, classification, and regulator.
Args:
cert: FDIC certificate number uniquely identifying the institution.
| Name | Required | Description | Default |
|---|---|---|---|
| cert | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns Call Report data for a specific reporting period and lists included categories (assets, deposits, etc.), which is transparent for a read-only tool.
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 concise with only 4 sentences, each adding value: purpose, return data summary, parameter explanation. No unnecessary words.
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 single-parameter tool with an output schema, the description covers the purpose, return data scope, and parameter meaning completely. No gaps.
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 0%, so the description compensates by explaining that 'cert' is an FDIC certificate number uniquely identifying the institution, adding essential context beyond the schema.
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 uses a specific verb ('Get') and resource ('detailed financial information for a specific FDIC-insured institution'), which clearly distinguishes it from siblings like 'get_bank_failures' or 'search_institutions'.
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?
The description clearly states the tool's purpose and the required parameter (cert), implying use when detailed financial data is needed. However, it does not explicitly mention when not to use this tool or provide direct comparisons to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all branch locations for an FDIC-insured institution.
Returns branch-level data from the Summary of Deposits (SOD) including
addresses, deposit amounts, branch type, and coordinates.
Args:
cert: FDIC certificate number uniquely identifying the institution.
| Name | Required | Description | Default |
|---|---|---|---|
| cert | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description bears full behavioral disclosure burden. It describes the return data (addresses, deposits, etc.) but does not state side effects, authorization needs, rate limits, or the read-only nature. It lacks explicit safety assurances.
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 reasonably concise: four sentences, front-loaded with the purpose. The 'Args:' section is somewhat unconventional but provides necessary parameter details given the sparse schema. No filler words.
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?
Given the tool's simplicity (one parameter, output schema present), the description covers purpose, input, and high-level output. It mentions the data source (SOD) and return fields. It could include error behavior, but overall sufficient.
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 schema has 0% description coverage for the 'cert' parameter. The description compensates fully by explaining it as 'FDIC certificate number uniquely identifying the institution', which adds crucial meaning beyond the schema type.
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 'Get all branch locations for an FDIC-insured institution', which is a specific verb-resource pair. It distinguishes from siblings like get_institution (institution-level data) and get_county_branches (branches by county), making the tool's role 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?
The description implies when to use this tool: when branch-level data for a specific institution is needed. However, it does not explicitly discuss when not to use it or mention alternatives (e.g., get_county_branches for county-based queries), leaving some guidance implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search FDIC-insured financial institutions by name.
Returns matching banks with key financial data from the most recent
Call Report (2024-06-30), sorted by total assets descending.
Args:
search: Institution name or partial name to search for.
limit: Maximum number of results to return (default 10, max 100).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| search | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description transparently discloses return data is from the most recent Call Report (2024-06-30) and sorted by total assets descending. It implies a read-only operation via 'search' and 'returns', but does not explicitly state non-destructiveness or authentication requirements.
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 concise and well-structured using a docstring format with an Args section. It contains no superfluous information, though the style is slightly formal.
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?
Given the two parameters, no enums, and presence of an output schema, the description covers purpose, parameters, and key behavioral details. It omits error cases and explicit read-only assurance, but these are minor relative to overall completeness.
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?
Despite 0% schema description coverage, the Args section fully explains both parameters: search is an institution name or partial name, and limit has a default and maximum. This adds substantial meaning beyond the bare property titles in the input schema.
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 tool searches FDIC-insured institutions by name and returns matching banks with key financial data sorted by total assets descending. This specific verb and resource combination, along with the search scope, distinguishes it from siblings like get_institution (which likely retrieves a single institution) and get_bank_failures.
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?
The description implies usage for searching institutions by name but does not provide explicit when-to-use or when-not-to-use guidance against siblings. It lacks selection criteria such as 'use this instead of get_institution when you need a list'.
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.
get_bank_failuresget_county_branchesget_institutionget_institution_branchessearch_institutionsFDIC MCP — FDIC BankFind Suite API (free, no auth)
Community bank intelligence: FDIC financials, peer benchmarking, HMDA lending and CRA posture.
SEC filings, financial statements, metrics, insider and institutional holdings as structured data
Delivers public regulatory and market data from 11 key sources such as FINRA, SEC, Census, FRED
Add one secure layer between your agents and this server.
