fx-news: one-shot per-pair intel summary. Parallel-fetches recent news (24h) + 7-day sentiment stats + trending headlines. The single call to make when asked 'what's going on with EUR-USD?' or any FX-pair analysis. 180s cache.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | Yes | Path parameter 'pair' (required). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses meaningful behavioral traits: parallel fetching, 24h news window, 7-day sentiment stats, trending headlines, and a 180s cache. This goes beyond the basic schema and gives the agent useful expectations about the tool's internal operations and data freshness, though it omits details like error behavior or exact output structure.
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 three sentences, each with a distinct purpose: identifying the tool type, detailing the data components, and stating the canonical use case. It is front-loaded with the core function and contains zero filler words.
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 the tool's simplicity (one param, no output schema) and the abundance of sibling tools, the description covers the essential context: what data is aggregated, the time windows, the caching behavior, and the primary use case. It does not explicitly describe the return payload, but the enumerated data components give a strong inference. A brief note on response structure would make it fully complete.
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?
The schema's pair description is essentially a placeholder ('Path parameter 'pair' (required)') with no semantic value. The tool description compensates by providing a concrete format example ('EUR-USD') and implicitly clarifying that the pair is a currency pair, which helps the agent form correct input. This exceeds the neutral baseline given the otherwise tautological schema.
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 states a specific verb+resource ('one-shot per-pair intel summary') and enumerates exactly what it fetches: recent news (24h), 7-day sentiment stats, and trending headlines. It also distinguishes itself from sibling tools by positioning as 'the single call to make' for FX-pair analysis, which is a clear differentiator.
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?
It provides explicit when-to-use guidance with concrete example queries ('what's going on with EUR-USD?') and states this is the go-to for any FX-pair analysis. However, it does not mention when not to use it or suggest specific alternative tools (e.g., the more granular forex news endpoints), so it stops short of a full 5.
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.
With 336 tools, there is substantial overlap. Over a dozen health/status tools share nearly identical 'is the system healthy?' descriptions (e.g., tengu_status, tengu_ready, tengu_ml_health, tengu_v3_system_health, tengu_v3_stream_status), and multiple single-ticker analysis (tengu_ml_predict, tengu_copilot_score_ticker, tengu_v3_intel_ml_prediction) and top-picks (tengu_copilot_top_picks, tengu_ml_top_picks, tengu_v3_trade_setups) tools have poorly defined boundaries. Agents would frequently misselect.
The server mixes no-version (tengu_crypto), v2 (tengu_v2_drift), v3 (tengu_v3_intel_*), and copilot (tengu_copilot_*) families, and within families there is inconsistent verb/noun ordering (tengu_v3_research_fetch_url vs tengu_v3_news_summary). While subfamilies like tengu_v3_private_markets_* are internally consistent, the overall naming pattern is chaotic and unpredictable.
336 tools is far beyond any reasonable tool set size, even for an all-in-one financial data platform. This extreme count creates choice paralysis, high latency in tool selection, and makes the server effectively unusable for autonomous agents. The calibration guideline marks 50+ as extreme; this is nearly 7x that threshold.
The platform covers a vast domain: equity and crypto prices, fundamentals, insider trading, options, news (including crypto and FX), private markets, streaming data, risk metrics, and execution planning. There are minor gaps (no direct multi-ticker comparison tool, no order placement), but the surface is remarkably comprehensive for an analysis-focused server.
