Skip to main content
Glama

LastLook Data

by io.github.zev-lll

Get FRED Data Series

get_series
Read-onlyIdempotent

Returns recent observations for any supported FRED data series. Use this to get current and historical values for mortgage rates, Treasury yields, Fed funds rate, CPI, SOFR, unemployment, GDP, energy prices, and more. Common use cases:

  • Current 30-yr mortgage rate: series_id=MORTGAGE30US, days=30

  • Current Fed funds rate: series_id=FEDFUNDS, days=30

  • Current 10-yr Treasury yield: series_id=DGS10, days=30

  • Current CPI (inflation): series_id=CPIAUCSL, days=30

  • Current WTI crude oil: series_id=DCOILWTICO, days=30 The most recent observation in the returned array is the current value.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysYesHistory window: 30 ($0.05), 90 ($0.10), or 365 ($0.25). Use 30 for current/recent values.
series_idYesFRED series ID. Use IORB for Interest on Reserve Balances, EFFR for Effective Fed Funds Rate, MORTGAGE30US for 30-yr mortgage rate, SAHMREALTIME for Sahm Rule, etc.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
endYesEnd date of the series window
countYesNumber of observations returned
labelYesHuman-readable series name
startYesStart date of the series window
series_idYesFRED series identifier
current_dateYesDate of the most recent observation
observationsYesAll observations in the window
current_valueYesMost recent observed value

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds a valuable behavioral detail: 'The most recent observation in the returned array is the current value,' which clarifies output ordering and how to extract the latest data point. No contradictions 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.

Conciseness5/5

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

The description is well-structured and front-loaded, with a clear first sentence followed by a bulleted list of five specific, actionable examples. The final note about the most recent observation is a critical piece of usage information. No fluff or redundant content; every line 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?

Given the tool's moderate complexity, rich annotations, complete parameter schema, and presence of an output schema, the description covers the core purpose, provides common use cases, and clarifies output interpretation. It could be slightly more explicit about how it relates to sibling tools, but overall it is sufficiently complete for an agent to use correctly.

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 both parameters fully described, including enums and guidance like 'Use 30 for current/recent values.' The description's examples reinforce common series_id/day combinations but do not add substantial semantics beyond what the schema already provides, so a baseline score of 3 is appropriate.

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 description clearly states the tool returns recent observations for any supported FRED data series, listing a wide range of economic indicators. This distinguishes it from sibling tools like get_current_value or get_value_by_date that focus on single values or specific dates, though it does not explicitly name these alternatives.

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 description provides clear context for when to use the tool ('Use this to get current and historical values') and includes five concrete common use cases with exact series_id and days parameters. It does not explicitly mention when not to use it or name alternative tools, but the examples give strong practical guidance.

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

All LastLook Data toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

The tool set has several overlapping functions, particularly among the bundle tools (e.g., get_bundle_context_brief vs get_bundle_macro both provide macro indicators, and get_bundle_rate_environment overlaps with get_yield_curve and get_policy_spread). Individual current/history/date tools are distinct but some redundancy exists (e.g., get_treasury_yield_current vs get_current_value for DGS30). Descriptions help differentiate purposes, but agents may still hesitate when selecting between similar bundles.

Naming Consistency4/5

All tool names begin with the verb 'get_' and use snake_case, creating a consistent pattern. The bundle tools are uniformly prefixed with 'get_bundle_', and individual data tools follow a get_[entity]_[modifier] structure (e.g., get_fx_rate_current, get_fx_rate_by_date, get_fx_rate_series). Minor deviations exist (e.g., get_series, get_current_value, get_value_by_date are less descriptive of the underlying entity), but overall the naming is predictable and readable.

Tool Count3/5

With 24 tools, the server is on the heavy side of the typical range. The broad domain (macro data, mortgage, crypto, FX, treasury, EDGAR) justifies many tools, but some could potentially be consolidated (e.g., individual rate tools vs rate bundles). The count does not feel overwhelming, but it is borderline heavy.

Completeness4/5

The server covers a wide range of economic and financial data with both bundled and granular views. It includes current, historical, and date-specific retrievals for FRED series, FX, and crypto, plus specialized tools for mortgages, recession, and yield curves. Minor gaps exist, such as no way to list all supported FRED series or full financial statements for EDGAR, but the core lifecycle of data querying is well covered.

Resources