Pricing/details for a CSV of every FDIC-insured bank's stress metrics from its own Call Report.
Scored across 2 tools
The two tools are clearly distinct: one provides dataset-level metadata and pricing, while the other returns metrics for a single bank. There is no overlap in purpose or output.
Both tool names follow a consistent snake_case verb_object pattern: get_bank_stress_dataset_info and lookup_bank_stress_metrics. The verbs and objects are descriptive and predictable.
Two tools is on the thin side, though the narrow read-only dataset domain partially justifies the small surface. The tools each have a clear purpose, but the set feels minimal.
The server covers dataset info and single-bank lookups, but lacks bulk retrieval, search, or a way to access the full dataset itself. Given the stated purpose around a licensable CSV dataset, this is a notable gap.
Get details and pricing for the US Bank Regulatory Stress Dataset: a flat CSV covering every FDIC-insured bank's balance-sheet stress metrics (AOCI burden on capital, uninsured deposit ratio, non-performing loan ratio, and core balance-sheet figures) computed directly from each bank's own public FFIEC Call Report. Useful for an agent building a bank-screening or credit-risk model that needs a licensable raw data input instead of scraping regulatory filings itself.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds beneficial context about dataset source and contents, but does not disclose specifics like return format, pagination, or any access restrictions. With annotations bearing the safety burden, the description adds value but not deep behavioral detail, so a 3 is appropriate.
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 two sentences but front-loads the core purpose ('Get details and pricing') and then efficiently packs in dataset composition, source, and use case. Every sentence earns its place without fluff. It is structured logically from action to context to application.
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, read-only info tool with no output schema, the description is remarkably complete. It tells the agent what data is available (specific metrics), where it originates (FFIEC Call Reports), and when to use it (model building vs. scraping). Nothing needed to invoke correctly is missing.
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?
There are zero parameters, so the description correctly omits parameter details. Per the rubric, 0 params yields a baseline of 4. The schema coverage is effectively 100% (empty schema), so no compensation is needed. The description's context about the dataset is supplementary.
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 states a clear verb ('Get') and a specific resource ('details and pricing for the US Bank Regulatory Stress Dataset'). It elaborates on what the dataset is (flat CSV of FDIC-insured banks' stress metrics from FFIEC Call Reports) and even hints at alternatives by contrasting with scraping regulatory filings. This goes well beyond a tautology and fully distinguishes the tool's purpose.
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 provides explicit contextual usage: 'Useful for an agent building a bank-screening or credit-risk model that needs a licensable raw data input instead of scraping regulatory filings itself.' This tells when to use it and implies an alternative (scraping), though it doesn't explicitly state 'do not use if...' or list sibling tools. Since there are no siblings, this is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up one US bank's balance-sheet stress metrics, computed from that bank's own FFIEC Call Report and citable as an official-source figure: AOCI burden on capital (how much of equity unrealised securities losses have eaten), uninsured deposit ratio, non-performing loan ratio, total assets and state. Covers all 4,296 FDIC-insured institutions for 2026 Q2 (filed as of 06/30/2026). Use this when an agent needs a grounded answer to "how stressed is this bank?" instead of guessing from memory or reading a filing by hand. Free, no key. One institution per call.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Institution name or a distinctive part of it, e.g. "CITIBANK, N.A." or "Zions". Minimum 3 characters. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: the data source ('computed from that bank's own FFIEC Call Report'), official citability, coverage ('2026 Q2'), and the 'Free, no key' and 'One institution per call' constraints. No contradiction with annotations.
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 slightly long but well-organized: the main action is front-loaded, followed by a list of returned metrics, scope, usage guidance, and constraints. Every sentence carries useful information; no filler. It could be trimmed slightly but remains appropriately sized for the tool's 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?
For a single-parameter, read-only lookup with no output schema, the description is quite complete: it lists all returned metrics, specifies the data source, coverage date, institution count, and usage context. It does not describe the exact return format or behavior on invalid names, but the listed metrics and annotations provide enough for an agent to invoke it correctly.
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 input schema has 100% description coverage for the single 'name' parameter, already explaining it expects an institution name or distinctive part and a 3-character minimum. The tool description adds only minor reinforcement ('One institution per call') and does not substantially augment parameter semantics beyond the schema, so the baseline of 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?
The description states a specific verb ('Look up'), a precise resource ('one US bank's balance-sheet stress metrics'), and enumerates the exact metrics it returns (AOCI burden, uninsured deposit ratio, non-performing loan ratio, total assets, state). It clearly differentiates from the sibling tool 'get_bank_stress_dataset_info' by focusing on individual institution lookup rather than dataset-level metadata.
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 an explicit trigger: 'Use this when an agent needs a grounded answer to "how stressed is this bank?" instead of guessing from memory or reading a filing by hand.' It also notes practical constraints ('Free, no key. One institution per call.') and scope ('Covers all 4,296 FDIC-insured institutions'). It does not explicitly mention the sibling tool or when not to use it, but the context is strong enough to route an agent.
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.
lookup_bank_stress_metricsget_bank_stress_dataset_infoBank financials, branch locations, deposit data, and failure history from FDIC
FFIEC Call Reports MCP — US bank line-item detail (fleet #338).
Community bank intelligence: FDIC financials, peer benchmarking, HMDA lending and CRA posture.
Read-only U.S. mortgage market, lender, GSE performance, and servicing analytics.
Add one secure layer between your agents and this server.
