Skip to main content
Glama

NCUA credit union data

by io.github.bnovarini
OverviewDiscussionsAdmin

metric_series

Time series of one metric or reported field. Give cu_number for one credit union. Otherwise it aggregates all federally insured credit unions matching the optional state (2-letter code) / peer_group (1-6) / min_assets filters: aggregate='median' (default for ratios), 'mean', 'sum' (default for dollar and count fields; not allowed on ratios), 'count' (how many credit unions report the field), 'ratio_of_sums' (sum of field / sum of the denominator field, e.g. shares_certificates over total_shares_and_deposits), or 'pooled' (the system-wide version of a ratio metric: total numerators over total denominators, not a median of credit unions; available for efficiency_ratio, delinquency_rate, loan_to_share, loans_to_assets, net_worth_to_assets, net_worth_ratio_ex_cecl, allowance_to_loans, mix_auto, net_chargeoff_rate, roa_year_end_assets, nim_year_end_assets, loan_yield, cost_of_shares, opex_to_assets, the NCUA-basis ratios (roa_ncua_ytd, nim_ncua_ytd, loan_yield_ncua_ytd, cost_of_funds_ncua_ytd, net_chargeoff_rate_ncua_ytd; pooled values reproduce NCUA's published ROA, NIM and net charge-off ratio), the single-quarter ratios (roa_quarterly and the like) and the growth metrics asset/loan/share/member_growth_yoy, which compare the same credit unions a year apart). Median and mean treat every credit union equally, tiny ones included. Year-to-date fields (basis year_to_date in list_fields: income, expenses, charge-offs, loans granted) are returned per quarter by default (quarterly=true: this quarter minus the prior quarter of the same year); quarterly=false returns the raw year-to-date figure, which resets each January. Each row carries basis (and unit for percent-x100 fields); rows with no data explain why. group_by='peer_group' or 'state' returns one row per group (defaults to the latest quarter). Series that cross the 2023 CECL accounting change carry a break_note. Range in quarters like 2021-12; the data runs 2018-03 to the latest quarter. Metrics: asset_growth_yoy (Total assets versus the same quarter one year earlier); loan_growth_yoy (Total loans versus the same quarter one year earlier); share_growth_yoy (Total shares and deposits versus one year earlier); member_growth_yoy (Members versus one year earlier); auto_loan_growth_yoy (New plus used vehicle loans versus one year earlier); first_lien_growth_yoy (First-lien 1-4 family loans versus one year earlier); loan_to_share (Loans divided by total shares and deposits); loans_to_assets (Loans divided by total assets); net_worth_to_assets (Net worth divided by total assets (1.0 = 100%)); allowance_to_loans (Allowance for credit losses divided by total loans); net_worth_ratio_ex_cecl (Net worth minus the CECL transition provision, over assets); deposit_mix_share_drafts (Share draft (checking) accounts as a share of total shares and deposits); deposit_mix_regular (Regular shares as a share of total shares and deposits); deposit_mix_money_market (Money market shares as a share of total shares and deposits); deposit_mix_certificates (Share certificates as a share of total shares and deposits); deposit_mix_ira_keogh (IRA and Keogh accounts as a share of total shares and deposits); deposit_mix_non_member (Non-member deposits as a share of total shares and deposits); avg_balance_per_listed_account (Total shares and deposits over the count of share draft, certificate, money market, IRA a…); employees_fte_estimate (Full-time employees plus half of part-time employees); members_per_fte (Members per estimated full-time-equivalent employee); assets_per_fte (Assets per estimated full-time-equivalent employee); compensation_per_fte (Annualized employee compensation and benefits per estimated FTE); operating_expense_per_fte (Annualized non-interest expense per estimated FTE); assets_per_branch (Assets per branch); members_per_branch (Members per branch); compensation_share_of_opex (Employee compensation and benefits as a share of non-interest expense); loans_per_member (Average loan dollars per member); shares_per_member (Average shares and deposits per member); mix_auto (New plus used vehicle loans as a share of total loans); mix_residential_real_estate (First lien, junior lien and other real estate loans as a share of total loans); mix_credit_card (Credit card loans as a share of total loans); mix_commercial (Commercial loans as a share of total loans); delinquency_rate (Loans delinquent two or more months divided by total loans); auto_delinquency_rate (Reportable delinquent vehicle loans divided by vehicle loans); credit_card_delinquency_rate (Delinquent credit card loans divided by credit card loans); net_chargeoff_rate ((Charge-offs minus recoveries), annualized from year to date, over year-end loans); net_chargeoff_rate_avg_loans_4q (Net charge-offs annualized from year to date, over the average of the last four quarter-e…); provision_to_loans (Provision (credit loss expense) annualized over year-end loans); roa_year_end_assets (Return on assets: net income annualized from year to date, over year-end assets); roa_avg_assets_4q (Return on assets: net income annualized from year to date, over the average of the last f…); nim_year_end_assets (Net interest margin: (interest income minus interest expense) annualized from year to dat…); nim_avg_assets_4q (Net interest margin (NIM): same, over the four-quarter average of assets); loan_yield (Yield on loans: interest on loans annualized from year to date, over year-end loans); cost_of_shares (Cost of shares: total interest expense annualized from year to date, over shares and depo…); efficiency_ratio (Non-interest expense divided by (net interest income plus non-interest income)); opex_to_assets (Non-interest expense annualized over assets); fee_share_of_non_interest_income (Fee income divided by non-interest income); net_income_quarter (Net income for the single quarter (year-to-date minus prior quarter)); interest_income_quarter (Interest income for the single quarter); interest_expense_quarter (Interest expense for the single quarter); non_interest_expense_quarter (Non-interest expense for the single quarter); provision_quarter (Provision for loan losses for the single quarter); roa_ncua_ytd (Return on average assets on NCUA's basis: year-to-date net income annualized, over the av…); nim_ncua_ytd (Net interest margin (NIM) on NCUA's basis: (interest income minus interest expense) annua…); loan_yield_ncua_ytd (Yield on loans on NCUA's basis: interest on loans annualized from year to date, over the …); cost_of_funds_ncua_ytd (Cost of funds on NCUA's basis: total interest expense annualized from year to date, over …); net_chargeoff_rate_ncua_ytd (Net charge-off rate on NCUA's basis: (charge-offs minus recoveries) annualized from year …); roa_quarterly (Return on assets for the single quarter: the quarter's net income times 4, over the avera…); nim_quarterly (Net interest margin (NIM) for the single quarter: (interest income minus expense) for the…); loan_yield_quarterly (Yield on loans for the single quarter: the quarter's interest on loans times 4, over the …); cost_of_funds_quarterly (Cost of funds for the single quarter: the quarter's interest expense times 4, over the av…); net_chargeoff_rate_quarterly (Net charge-off rate for the single quarter: the quarter's (charge-offs minus recoveries) …); interest_on_loans_quarter (Interest on loans for the single quarter (year-to-date minus prior quarter)); net_chargeoffs_quarter (Charge-offs minus recoveries for the single quarter)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNo
fieldYes
startNo
stateNo
group_byNo
aggregateNo
cu_numberNo
quarterlyNo
min_assetsNo
peer_groupNo
denominatorNo
year_end_onlyNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / peer_group / anyOf
      Previous value: -[
-  {
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
  2. Changed2 schema fields changed
    • addedInput schema / properties / min_assets
      Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Min Assets"
+}
    • addedInput schema / properties / quarterly
      Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Quarterly"
+}
  3. Changed2 schema fields changed
    • addedInput schema / properties / denominator
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Denominator"
+}
    • addedInput schema / properties / group_by
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Group By"
+}
  4. First observed

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so well: it discloses the data range (2018-03 to latest quarter), the default aggregate per field type, the restriction that sum is disallowed on ratios, the pooled availability list, the CECL break_note, and that rows with no data explain why. Auth, rate limits, and pagination remain undisclosed, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The prose is a single dense wall with a very long run-on metric catalog (dozens of metrics separated by semicolons, some truncated mid-word such as "IRA a…"), and it duplicates cataloging that the sibling list_fields already performs. Key behaviors like the default-aggregate rule are buried mid-paragraph rather than front-loaded, hurting scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter aggregation tool with an output schema (so return values need not be described), the description is nearly complete: modes, filters, aggregation semantics, quarterly handling, and metric definitions are all present. The unexplained year_end_only parameter is the only notable gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate across 12 parameters, and it largely does: cu_number, state (2-letter code), peer_group (1-6), min_assets, the full aggregate enum with defaults, group_by, quarterly semantics, start/end quarter format, and denominator via the ratio_of_sums example are all explained. The only uncovered parameter is year_end_only, which is never mentioned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource ("Time series of one metric or reported field") and immediately splits the two operating modes: single CU via cu_number versus aggregation across federally insured credit unions. This is clear enough to distinguish from peers, though it never names query_metrics or peer_compare, which an agent must infer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It effectively states the conditions that select behavior: give cu_number for one credit union, otherwise it aggregates with optional state/peer_group/min_assets filters, and group_by returns one row per group. However, it offers no explicit when-to-use-this-versus-alternatives routing against siblings like query_metrics or peer_compare, so 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.

All NCUA credit union data toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources