fx_strengthRanked strength leaderboard for the past N days. For each currency in the basket (g10 or majors), the average move across every pair it participates in. Strongest → weakest with per-currency label.
| Name | Required | Description | Default |
|---|---|---|---|
| basket | No | g10 | |
| horizon_days | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish this as a safe, read-only, idempotent operation, so the description's additional burden is low. It adds meaningful behavioral context by explaining the ranking methodology: averaging each currency's move across every pair in the basket and ordering by strength. No contradictions with annotations were found.
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?
Three sentences deliver the core purpose, the calculation methodology, and the output ordering with no redundancy. The key term 'strength leaderboard' is front-loaded, and the next sentences earn their place by clarifying what 'strength' means.
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 simple read-only tool with two optional parameters and no output schema, the description covers the essential needed details: time window, basket choices, computation, and return ordering. It is slightly incomplete in not specifying the return label format or whether moves are expressed in percentages or pips, but this is a modest gap given the tool's low complexity.
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 input schema has 0% description coverage, so the description must compensate. It does so by explaining that 'basket' limits the leaderboard to g10 or majors and that 'past N days' maps to horizon_days. This gives semantic meaning beyond the raw enum/default values, though it stops short of defining exact move units or basket membership details.
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?
States a specific verb and deliverable: a 'ranked strength leaderboard' over the past N days. It further specifies the resource (g10 or majors basket) and the output structure (strongest to weakest, per-currency label), making it clearly distinct from related FX tools like fx_volatility_leaders.
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 phrasing 'ranked strength leaderboard' implies the tool is for comparing relative currency strength over a horizon, and the description gives methodological context. However, it does not explicitly say when to use this tool versus alternatives such as fx_movers, fx_correlation, or fx_volatility_leaders, nor does it name exclusions.
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.
Multiple tools have genuinely blurry boundaries: company_change vs company_changes differ only by singular/plural yet serve different purposes, company_domain vs company_classify vs company_lookup_auto all accept a domain, geo_zip_lookup vs geo_enrich vs geo_zip_batch all return ZIP profiles, and email_validate subsumes much of email_disposable and email_free_provider. The domain prefixes help narrow search space, but within many domains an agent cannot reliably predict which tool is the right one.
All 129 tools uniformly follow a snake_case [domain]_[topic] convention (company_, fx_, geo_, dns_, weather_, tax_), which is highly predictable and consistent. Minor deviations include the confusing company_change/company_changes pair, and inconsistent suffix usage (_batch appears on address_validate_batch, company_domains_batch, geo_zip_batch but not on equivalent lookup tools elsewhere).
129 tools far exceeds the 50+ extreem-mismatch threshold, bundling roughly 28 unrelated data domains (weather, fx, tax, ccompany, dns, jobs, flight, email, phone, tax...) into a single MCP surface. Even focusing on one domain forces the agent to load an enormous unrelated tool list; this should be split into many smaller domain-specific servers.
Per-domain coverage is impressively thorough: weather spans current/forecast/hourly/historical/normals/marine/route/air-quality, fx covers rates/convert/historical/volatility/correlation/strenth, and company includes lookup/enrichment/networks/timeline/peer-comparison plus six buyer-tuned signals with profile-introspection tools. Minor gaps like flight being historical-only and smtp probes skipping major email providers are documented scope decisions rather than dead ends.