One-call combined macro snapshot for AI trading agents.
Returns: latest 10Y Treasury yield, full yield curve, CPI YoY, headline unemployment, effective fed funds rate, and the 5 most recent Treasury auction results. Designed so an LLM can answer "what's the macro picture right now?" with one tool-call.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, indicating no side effects. The description adds value by enumerating the exact data returned (list of economic indicators), which goes beyond the annotation. No contradictory behavior is mentioned.
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: first states the tool's essence, second lists return data, third explains design intent. It is front-loaded and every sentence adds value without redundancy.
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?
Given no parameters and no output schema, the description completely specifies what the tool returns with a clear list. It distinguishes from siblings, and the context is sufficient for an agent to decide to use it. Annotations cover safety.
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 no parameters, and schema coverage is 100% (trivial). The description does not need to add parameter semantics but provides context on the tool's purpose, which is sufficient. Baseline for 0 params is 4.
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 clearly states the tool returns a combined macro snapshot including specific data points (10Y yield, yield curve, CPI, unemployment, fed funds rate, auction results). It distinguishes itself from siblings by being a 'one-call combined' tool, with siblings focusing on individual data sources like auction results or FRED series.
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 explicitly states the tool is 'designed so an LLM can answer what's the macro picture right now?' with one call, implying usage context. However, it does not explicitly state when not to use it or name alternatives, though sibling tools are implied for specific data needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes: auction results vs upcoming auctions, yield curve vs dashboard snapshot. However, get_fred_series can retrieve Treasury yields and auction-related data, overlapping with the other specialized tools, causing minor ambiguity.
All tool names follow a consistent 'get_' prefix with snake_case nouns describing the data (e.g., get_auction_results, get_treasury_yield_curve). No deviations or mixed conventions.
Five tools is well-suited for this domain: two for auctions (past and future), one for yield curves, one for a macro dashboard, and one generic FRED series fetcher. The scope is focused and each tool serves a clear purpose.
The tool set covers core macro and Treasury data operations: historical auction results, upcoming auctions, yield curves, a combined dashboard, and the ability to fetch any FRED series. No obvious gaps exist for read-only data retrieval.