Requires a ChainHelix API key as bearer token, or 2 cents per call paid over Binance b402 in USDT, USDC, USD1 or U on BNB Smart Chain, or over x402 in USDC on the Base network. Pairwise correlation of hourly returns across the nine chains. window in days default 7 max 30
| Name | Required | Description | Default |
|---|---|---|---|
| window | No |
| Name | Required | Description | Default |
|---|---|---|---|
| mean | No | ||
| pairs | Yes | ||
| windowDays | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden. It discloses significant behavioral aspects: authentication via bearer token, cost per call, payment methods, window default (7 days), maximum (30 days), and the computation basis (hourly returns across nine chains). This goes beyond a basic purpose statement, though it omits details about output format or potential rate limits.
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 run-on sentence that mixes payment/billing information with the functional description. It front-loads payment details rather than the tool's purpose, making it structurally messy. The information could be split into separate sentences for clarity and conciseness.
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 tool with one parameter and an output schema, the description covers the essential context: what it does, the data scope, authentication/cost, and parameter constraints. It does not explain the nine chains or use cases, but that might be considered domain knowledge. Overall, it is sufficiently complete for an agent to decide whether to invoke it.
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 only defines 'window' as a number with no description (0% schema coverage). The description adds meaningful semantics: 'window in days default 7 max 30', clarifying units, default, and valid range. For a single-parameter tool, this compensates well for the schema's lack of context.
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 core purpose is clear: 'Pairwise correlation of hourly returns across the nine chains.' It identifies the specific resource (nine chains) and the analysis performed. However, the description starts with payment/auth details, which obscure the main purpose, and it does not explicitly differentiate from sibling tools like prices or market_state.
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 provides authentication/payment requirements but no guidance on when to use this tool versus alternatives. There is no mention of scenarios where correlation analysis is appropriate or how it compares to related tools such as whale_flows or latest_signals.
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 clearly distinct purposes, but some overlap exists among report tools (situation_report, deep_report, market_state) and spec tools (attest_spec, proof_spec). These could confuse an agent selecting the most appropriate endpoint.
Tool names use consistent snake_case and are descriptive, but follow mixed patterns: verb_noun for actions (buy_key, list_attestations) and bare nouns or noun phrases for data endpoints (prices, congestion, wall_map). This is readable but not fully uniform.
With 26 tools, the set is heavy and covers multiple domains (attestation, market data, key management, webhooks). It sits just above the borderline for comfort, but the breadth is justifiable given the server's multi-purpose nature.
The tool surface provides full lifecycle coverage for attestation (create, read, verify), key management (buy, claim, status), and webhooks (register, status, unregister), plus a wide range of market data endpoints. There are no obvious gaps or dead ends.