cnb_monthly_averagesMonthly average exchange rates for ONE currency against CZK, across all available years. Returns month (e.g. "JAN"), year, currencyCode, amount and average. Useful for historical trend/year-over-year comparisons of a currency vs CZK. Verified live.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Label language: "EN" (default) or "CZ". | |
| currency | Yes | ISO currency code, e.g. "USD", "EUR" (required). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) already cover safety and idempotency. Description adds 'Verified live' which is vague and does not disclose rate limits, data freshness, or other traits. No contradiction, but minimal extra behavioral context beyond annotations.
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?
Four short sentences, front-loaded with purpose and output format. The sentence 'Verified live.' is somewhat extraneous but not harmful. Could be slightly more compact, but overall efficient.
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 simple tool (2 parameters, no output schema, no nested objects), description covers purpose, input, output structure, and use case. Missing details like date range limits or pagination, but acceptable for a straightforward lookup tool.
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?
Schema coverage is 100% with clear descriptions for lang and currency. Description emphasizes 'ONE currency' but does not add new meaning beyond the schema. Baseline score of 3 is appropriate as schema carries the weight.
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?
Description specifies verb ('returns'), resource ('monthly average exchange rates for ONE currency against CZK'), and scope ('across all available years'). It clearly differentiates from siblings like cnb_exchange_rates (likely daily) and cnb_exchange_rates_currency_month (single month) by emphasizing 'monthly averages' and 'ONE currency' over all years.
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?
States usefulness for 'historical trend/year-over-year comparisons', providing clear context. However, it does not explicitly mention when not to use or name alternative tools, leaving some ambiguity compared to highest bar.
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.
Tools have distinct purposes overall, but some pairs (e.g., ask_pipeworx vs ask_pipeworx_grounded, entity_profile vs recent_changes) could cause agent confusion without careful reading. Descriptions mitigate overlap, so only minor ambiguity.
Most tools use snake_case with verb_noun or noun_verb patterns, but several single-word verbs (forget, recall, remember, subscribe) and a few inconsistent forms (czeonia, pribor) break uniformity. Still, the pattern is largely predictable.
31 tools is high but justified for a multi-domain data gateway covering finance, economics, FDA, betting, and subscriptions. Each tool has a clear role, though the count pushes the upper bound for easy scanning.
The tool set comprehensively covers its stated domains: entity resolution, financial data, exchange rates, interest rates, SEC filings, FDA, Polymarket analysis, subscriptions, and utility memory. No obvious gaps given its purpose as a data retrieval and analysis server.