Skip to main content
Glama
Sign In

Bls

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Bls Get Series

bls_get_series
Read-onlyIdempotent

Fetch historical time series data for employment, inflation, wages, productivity, or housing. Returns dated data points with values. Provide a BLS series ID (e.g., "CES0000000001" for total nonfarm payroll employment, the headline Employment Situation jobs number; "LNS14000000" for the unemployment rate). "PAYEMS" is the FRED id for the same series, not a BLS id.

Input Schema

NameRequiredDescriptionDefault
_apiKeyNoBLS registration key (optional, increases rate limits)
end_yearNoEnd year (e.g., "2024"). Default: current year.
series_idYesBLS series ID (e.g., "LNS14000000" for unemployment rate). For multiple series, comma-separate them (e.g., "LNS14000000,CES0000000001").
start_yearNoStart year (e.g., "2023"). Default: current year minus 2.

Output Schema

NameRequiredDescriptionDefault
seriesYesArray of time series data
statusYesAPI response status (e.g., 'REQUEST_PROCESSED')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "_apiKey": "your-bls-api-key",
-    "series_id": "LNS14000000"
-  },
-  {
-    "_apiKey": "your-bls-api-key",
-    "end_year": "2024",
-    "series_id": "PAYEMS,CES0000000001",
-    "start_year": "2020"
-  },
-  {
-    "series_id": "EIUIR",
-    "start_year": "2023"
-  }
-]New value: +[
+  {
+    "series_id": "LNS14000000"
+  },
+  {
+    "end_year": "2024",
+    "series_id": "PAYEMS,CES0000000001",
+    "start_year": "2020"
+  },
+  {
+    "series_id": "EIUIR",
+    "start_year": "2023"
+  }
+]
  2. Changed2 schema fields changed
    • addedOutput schema / properties / series / items / properties / count
      Added value: +{
+  "description": "Number of data points for this series — BLS returns every point in the requested year range, so nothing is truncated.",
+  "type": "number"
+}
    • addedOutput schema / properties / series / items / properties / observation_order
      Added value: +{
+  "description": "Order of the `data` array. BLS returns each series newest-first.",
+  "enum": [
+    "newest_first"
+  ],
+  "type": "string"
+}
  3. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "_apiKey": "your-bls-api-key",
-    "series_id": "LNS14000000"
-  },
-  {
-    "_apiKey": "your-bls-api-key",
-    "end_year": "2024",
-    "series_id": "PAYEMS,CES0000000001",
-    "start_year": "2020"
-  }
-]New value: +[
+  {
+    "_apiKey": "your-bls-api-key",
+    "series_id": "LNS14000000"
+  },
+  {
+    "_apiKey": "your-bls-api-key",
+    "end_year": "2024",
+    "series_id": "PAYEMS,CES0000000001",
+    "start_year": "2020"
+  },
+  {
+    "series_id": "EIUIR",
+    "start_year": "2023"
+  }
+]
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "series": {
+      "description": "Array of time series data",
+      "items": {
+        "properties": {
+          "data": {
+            "description": "Time series data points",
+            "items": {
+              "properties": {
+                "latest": {
+                  "description": "Whether this is the latest data point",
+                  "type": "boolean"
+                },
+                "period": {
+                  "description": "Period code (e.g., M01 for January)",
+                  "type": "string"
+                },
+                "period_name": {
+                  "description": "Human-readable period name (e.g., 'January')",
+                  "type": "string"
+                },
+                "value": {
+                  "description": "Data point value",
+                  "type": "string"
+                },
+                "year": {
+                  "description": "Year of the data point",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "year",
+                "period",
+                "period_name",
+                "value",
+                "latest"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "series_id": {
+            "description": "BLS series identifier",
+            "type": "string"
+          }
+        },
+        "required": [
+          "series_id",
+          "data"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "API response status (e.g., 'REQUEST_PROCESSED')",
+      "type": "string"
+    }
+  },
+  "required": [
+    "status",
+    "series"
+  ],
+  "type": "object"
+}
  5. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "_apiKey": "your-bls-api-key",
+    "series_id": "LNS14000000"
+  },
+  {
+    "_apiKey": "your-bls-api-key",
+    "end_year": "2024",
+    "series_id": "PAYEMS,CES0000000001",
+    "start_year": "2020"
+  }
+]
  6. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare this is a read-only, idempotent, non-destructive open-world call, so safety is covered. The description adds that it returns dated data points with values, which is mildly useful but largely duplicated by the output schema. It says nothing about multi-series response shape, missing/invalid series behavior, or rate-limit implications of omitting _apiKey.

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

Conciseness4/5

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

Purpose is front-loaded in the first sentence and the return shape follows immediately, so an agent gets the essentials in one pass. Slightly over-padded with parenthetical examples in the middle sentence, but nothing is wasted outright.

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?

With a full output schema, complete parameter documentation, and comprehensive annotations, the description only needs to add the series-ID domain knowledge, which it does. The remaining gap is routing against the four sibling BLS tools, which an agent would still have to guess at.

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 100%, so the baseline is 3; the description earns above that by adding real semantic content the schema lacks: what CES0000000001 actually represents (the headline jobs number) and the gotcha that FRED's "PAYEMS" is not a valid BLS id. It does not address start_year/end_year semantics, but those are fully documented in-schema.

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?

States a specific verb and resource ("Fetch historical time series data") and enumerates the domains covered (employment, inflation, wages, productivity, housing), which separates it from a generic data fetch. It implicitly distinguishes itself from the sibling bls_latest by emphasizing historical series, but never names that sibling or bls_search/bls_popular_series explicitly.

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?

The description tells the agent it must supply a BLS series ID and gives concrete example IDs, which is real invocation guidance. It never states when to prefer this over bls_latest, bls_search, or bls_popular_series, and gives no exclusions, so the routing decision is left to inference from the word "historical."

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Bls 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