Finance Signal Bundle - get live computed signal: BTC NUPL (net unrealized profit/loss) from BGeometrics, lagged 1 day. NUPL<0 capitulation zone, >0.75 bubble top. Market sentiment cycle anc Price 0.01 via x402 (USDC on Base).
| Name | Required | Description | Default |
|---|---|---|---|
| wallet | No | optional 0x wallet for X-Wallet free tier (free credits every month: 100 anonymous or 5000 with a bound wallet) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It mentions data lag (1 day) and source, but the payment/cost aspect is ambiguous: 'Price 0.01 via x402 (USDC on Base)' is unclear whether 'Price' is an output or a fee, and the typo 'anc' further obscures meaning. This ambiguity is significant for a tool that might charge users, and there is no clear statement of whether authentication or wallet is required at the tool level.
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 a single sentence and relatively short, but the final clause is confusing due to the typo 'anc' and the ambiguous 'Price 0.01 via x402' phrasing. It is not as clean or well-structured as ideal.
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?
The description covers the signal source, lag, and interpretation thresholds, but lacks a clear statement of what the return value looks like (e.g., numeric value, JSON object). More importantly, the payment requirement is muddled; for a paid API call, the cost/usage should be unambiguous. With no output schema, the description should compensate more.
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 description coverage is 100%, so the baseline is 3. The description does not mention the 'wallet' parameter, but the schema already provides a clear description including free tier credits, so the description need not compensate. No additional parameter meaning is added.
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 states the tool retrieves a live computed BTC NUPL signal, identifies the specific resource (BTC NUPL) and source (BGeometrics), and distinguishes it from sibling tool by naming the exact metric and its interpretation. The verb 'get' and resource are specific.
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 description gives clear context by explaining NUPL thresholds for sentiment interpretation (capitulation zone, bubble top), implying use cases for market sentiment assessment. It does not explicitly mention alternatives or when not to use, but the context is strong enough for a signal-specific tool.
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.
Nearly all 80+ processed_/signal_ tools share the same boilerplate description and overlapping coverage areas (e.g., processed_global_markets vs. processed_global_indices vs. signal_global_indices; processed_crypto_funding_rate vs. processed_crypto_funding_rates), so an agent cannot reliably distinguish them. The generic ai_gateway, fetch_data, and list_products also have somewhat fuzzy boundaries around data access. Only broad asset categories in the names provide any separation.
Core tools use verb-first imperative names (fetch_data, get_product_info, list_products), while the vast majority use adjective/noun prefixes (processed_*, signal_*), so the set mixes conventions. Within each cluster naming is consistent and all names are readable snake_case, but the 87-tool surface has no single predictable verb_noun pattern. Minor singular/plural inconsistencies like processed_crypto_funding_rate vs. processed_crypto_funding_rates add friction.
87 tools is an extremely large surface for an MCP server, and most are variant data products that could be one fetch_data call with a product identifier. This falls into the >50 extreme range. The generic list/get/fetch primitives make the 80+ product-specific endpoints especially redundant.
The core consumer flow is covered: list products, inspect product info, and fetch a product (with payment challenge handling). Missing wallet/credit/balance tools and search/filtering are notable but work-aroundable. For a read-only data marketplace the lifecycle is largely complete.