boi_exchange_rateCurrent Bank of Israel representative exchange rate for a single currency vs the Israeli Shekel (ILS), by 3-letter ISO code. Returns currentExchangeRate (shekels per unit), currentChange (%), unit, and lastUpdate. Note unit (e.g. JPY is per 100). Example keys: USD, EUR, GBP, JPY, CHF, CAD, AUD.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | 3-letter ISO currency code, e.g. "USD" or "EUR". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already show readOnlyHint, destructiveHint false. Description adds valuable behavioral details: returns currentExchangeRate (shekels per unit), currentChange, unit, and lastUpdate. Notes that unit may vary (JPY per 100). Contradicts no annotation.
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?
Two sentences, front-loaded with core purpose and return fields. Second sentence adds a key behavioral note and examples. No redundancy, 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 single parameter with full schema coverage, no output schema, description covers all needed aspects: input, returns, and special behavior. Complete for an AI agent to use correctly.
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% and describes 'key' as 3-letter ISO code. Description reinforces that and adds semantic nuance: example keys and note about unit (JPY per 100). Adds meaningful context beyond 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?
Description clearly states it gets current Bank of Israel exchange rate for a single currency vs ILS, using 3-letter ISO code. It lists return fields and distinguishes from sibling 'boi_exchange_rates' (plural) which likely returns multiple rates.
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?
Description specifies input as 3-letter ISO code and gives example keys. While it doesn't explicitly state when not to use, the sibling name 'boi_exchange_rates' implies that tool is for multiple currencies. Provides clear context for usage.
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 highly detailed descriptions that clarify their distinct roles, and the pipeworx/boi/polymarket families are individually distinguishable. However, ask_pipeworx_beta is explicitly described as currently identical to ask_pipeworx (a true duplicate), and the polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) share overlapping purpose and could cause misselection despite their lengthy docs.
Many tools follow a clear verb_noun pattern (compare_entities, discover_tools, resolve_entity, validate_claim), but a large subset uses noun-first or prefixed compound names (ai_visibility_check, bet_research, boi_exchange_rate, polymarket_arbitrage). The naming is readable and group-consistent (boi_*, polymarket_*, ask_pipeworx*) but the overall convention is mixed rather than uniform.
At 34 tools, the set exceeds the 25+ threshold for 'too many' and spans many unrelated domains (data lookup, prediction markets, memory, subscriptions, AI visibility, llms.txt generation, feedback). The broad scope explains the count, but many tools feel like add-on utilities rather than a tightly scoped server, making the surface feel bloated.
The core domain—authoritative structured data access—is extremely well covered: universal routing, grounded mode, deep research, entity profiles, comparisons, claim validation, resolution, discovery, and suggestions. Minor gaps exist (no explicit tool for fetching a pipeworx:// citation URI directly, no update operation for subscriptions), but agents can work around these via the router and existing subscription lifecycle tools.