Latest reference values (refreshed every 3 hours): crypto (BTC/ETH/SOL/XRP/BNB/ADA/USDT/USDC/DAI), FX (EUR/USD, USD/JPY, GBP/USD, USD/CNY, USD/CHF, AUD/USD, USD/CAD, USD/INR, USD/BRL), ECB main refinancing rate, US 10Y Treasury yield, US CPI YoY. Each carries its source and observation date — NOT real-time ticks.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It clearly states that data refreshes every 3 hours, includes its source and observation date, and explicitly warns that it is not real-time, preventing a common misunderstanding based on the tool name 'live_data'.
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 front-loaded with the core value proposition, followed by a precise list of supported data categories and a critical caveat. Every sentence earns its place, and there is no redundant or filler language.
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?
For a zero-parameter tool with no output schema, the description is largely self-sufficient: it names the assets, refresh interval, source/observation-date metadata, and the non-real-time caveat. It does not specify output format or units, but that is not required for correct invocation.
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 tool has zero parameters and the schema has 100% coverage, so the description does not need to explain parameter semantics. The listing of supported asset categories and symbols adds useful context beyond the empty 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 clearly identifies the tool as a provider of latest reference values across a specific set of crypto, FX, and macro assets. It is unambiguous about the resource, though it lacks an explicit verb and does not differentiate itself from sibling tools by name.
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 refresh cadence and the explicit 'NOT real-time ticks' statement imply when the tool should be used and when it should not, but no alternative tools or explicit selection criteria are mentioned. Usage guidance is present only implicitly.
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.
Each tool has a distinct retrieval mode: search/list for discovery, lookup/resolve_identifier for exact entity access, graph for relationships, live_data for reference values, and ingest_text for text extraction. Despite several retrieval tools, their input/output contracts are clearly separated in the descriptions.
Names are mostly lowercase and readable, but they mix single-word commands (graph, list, lookup, search), noun phrases (live_data), and verb_noun compounds (ingest_text, resolve_identifier). There is no consistent verb_noun pattern, so the set feels slightly ad hoc.
Seven tools cover the server's read-only knowledge-base scope without bloat: each operation (discover, resolve, look up, traverse, get live data, ingest text) maps to exactly one tool. This is well within the ideal 3–15 range.
The surface covers the main entity lifecycle: search/list to find, lookup/resolve_identifier to retrieve, graph to expand relationships, live_data for current values, and ingest_text for parsing text. Minor gaps such as schema introspection or historical time-series would require workarounds, but core workflows have no dead ends.