Skip to main content
Glama

search_series

Read-onlyIdempotent

Search FRED for economic data series by text query, returning matches with pagination metadata (total count, offset, limit).

Instructions

Search FRED for series matching text. Returns the matching series along with pagination metadata (total match count, offset, limit).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoSort direction.
textYesWords to search for, e.g. "unemployment rate". Must be non-empty.
limitNoMaximum number of results to return.
order_byNoField to order results by (default: search relevance).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesTotal number of matches across all pages.
limitYesPage-size limit that FRED applied.
offsetYesOffset of this page into the full result set.
seriesYesThe matching series on this page. FRED names the array `seriess` (sic) on the wire; we read that but emit the correctly-spelled `series` on output.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.11
  2. Removedv0.3.10
  3. Changed2 schema fields changedv0.3.9
    • changedInput schema / properties / text / description
      Previous value: -"Words to search for, e.g. \"unemployment rate\"."New value: +"Words to search for, e.g. \"unemployment rate\". Must be non-empty."
    • addedInput schema / properties / text / minLength
      Added value: +1
  4. Changed1 schema field changedv0.3.7
    • changedOutput schema / $defs / Series / description
      Previous value: -"Metadata describing a FRED series (the `fred/series` endpoint).\n\nALFRED vintage fields (`realtime_start` / `realtime_end`) are deferred for v1\nand ignored on the wire (ADR-0005). `last_updated` is kept as FRED's raw\nstring for now — FRED encodes it with a non-standard timezone offset (e.g.\n`2024-03-28 07:56:03-05`); a typed datetime is a later refinement."New value: +"Metadata describing a FRED series (the `fred/series` endpoint).\n\nThis `series` metadata endpoint's own ALFRED fields (`realtime_start` /\n`realtime_end`) are still ignored on the wire (ADR-0005); point-in-time\n*observations* are supported via [`Observation`](crate::Observation) and\n[`ObservationsRequest::realtime`](crate::ObservationsRequest::realtime)\n(ADR-0024). `last_updated` is kept as FRED's raw string for now — FRED\nencodes it with a non-standard timezone offset (e.g. `2024-03-28 07:56:03-05`);\na typed datetime is a later refinement."
  5. Changed1 schema field changedv0.3.6
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$defs": {
      +    "Frequency": {
      +      "type": "string"
      +    },
      +    "SeasonalAdjustment": {
      +      "type": "string"
      +    },
      +    "Series": {
      +      "description": "Metadata describing a FRED series (the `fred/series` endpoint).\n\nALFRED vintage fields (`realtime_start` / `realtime_end`) are deferred for v1\nand ignored on the wire (ADR-0005). `last_updated` is kept as FRED's raw\nstring for now — FRED encodes it with a non-standard timezone offset (e.g.\n`2024-03-28 07:56:03-05`); a typed datetime is a later refinement.",
      +      "properties": {
      +        "frequency": {
      +          "$ref": "#/$defs/Frequency",
      +          "description": "The series' native reporting frequency."
      +        },
      +        "id": {
      +          "$ref": "#/$defs/SeriesId",
      +          "description": "The series identifier."
      +        },
      +        "last_updated": {
      +          "description": "When FRED last updated the series, as FRED's raw timestamp string.",
      +          "type": "string"
      +        },
      +        "notes": {
      +          "default": null,
      +          "description": "Editorial notes, when present.",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "observation_end": {
      +          "description": "Date of the latest available observation.",
      +          "format": "date",
      +          "type": "string"
      +        },
      +        "observation_start": {
      +          "description": "Date of the earliest available observation.",
      +          "format": "date",
      +          "type": "string"
      +        },
      +        "popularity": {
      +          "description": "FRED popularity score (0–100).",
      +          "format": "uint32",
      +          "minimum": 0,
      +          "type": "integer"
      +        },
      +        "seasonal_adjustment": {
      +          "$ref": "#/$defs/SeasonalAdjustment",
      +          "description": "Whether/how the series is seasonally adjusted."
      +        },
      +        "title": {
      +          "description": "Human-readable title, e.g. `\"Real Gross National Product\"`.",
      +          "type": "string"
      +        },
      +        "units": {
      +          "description": "Free-form units description, e.g. `\"Billions of Chained 2017 Dollars\"`.\nThis is descriptive text, *not* the closed-vocabulary units transform\nused in observation requests (modelled separately, later).",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "id",
      +        "title",
      +        "observation_start",
      +        "observation_end",
      +        "frequency",
      +        "seasonal_adjustment",
      +        "units",
      +        "popularity",
      +        "notes",
      +        "last_updated"
      +      ],
      +      "type": "object"
      +    },
      +    "SeriesId": {
      +      "description": "A FRED series identifier, e.g. `GNPCA` or `UNRATE`.\n\nA newtype over `String` so a series id can't be silently swapped for another\nkind of identifier or an arbitrary string (see ADR-0005). Construction does\nno validation for now — FRED rejects malformed ids — but the newtype gives\nus a place to add it later without changing call sites.",
      +      "type": "string"
      +    }
      +  },
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "properties": {
      +    "count": {
      +      "description": "Total number of matches across all pages.",
      +      "format": "uint32",
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "limit": {
      +      "description": "Page-size limit that FRED applied.",
      +      "format": "uint32",
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "offset": {
      +      "description": "Offset of this page into the full result set.",
      +      "format": "uint32",
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "series": {
      +      "description": "The matching series on this page. FRED names the array `seriess` (sic) on\nthe wire; we read that but emit the correctly-spelled `series` on output.",
      +      "items": {
      +        "$ref": "#/$defs/Series"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "series",
      +    "count",
      +    "offset",
      +    "limit"
      +  ],
      +  "type": "object"
      +}
  6. First observedv0.3.2

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare read-only, open-world, and idempotent behavior. The description adds pagination metadata details (total count, offset, limit), which is useful context beyond annotations, but no additional side-effect information or edge cases.

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

Conciseness5/5

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

Two concise sentences, front-loaded with purpose, no fluff. Every word earns its place.

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 read-only search tool with an output schema, annotations, and fully described parameters, the description is adequate. It covers core behavior and return metadata without needing to explain every option.

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

Parameters3/5

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

Schema description coverage is 100% with all parameters documented (text, limit, order_by, sort). The description doesn't add parameter-level detail beyond mentioning 'text' implicitly, so it stays at baseline.

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

Purpose5/5

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

The description clearly states the verb 'Search', the resource 'FRED series', and the key parameter 'text'. It also mentions the return of pagination metadata, distinguishing it from tools like get_series (specific series retrieval) and other search-related tools for tags.

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

Usage Guidelines4/5

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

The context is clear: use this tool to find series by text. It doesn't explicitly name alternatives or exclusions, but the purpose strongly implies when to use it.

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