get_correlation[DRILL-DOWN] Return-correlation + beta of a coin to BTC and ETH over a 7d window of 15m log returns, plus its most/least correlated peers. Descriptive statistic (correlation is not causation). Same data as REST /correlation/{coin}.
| Name | Required | Description | Default |
|---|---|---|---|
| coin | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| coin | Yes | ||
| to_btc | No | ||
| to_eth | No | ||
| disclaimer | No | ||
| most_correlated | No | ||
| least_correlated | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral details: the 7d window, 15m log returns, inclusion of peers, and the caveat that correlation is not causation. It also notes parity with a REST endpoint, which helps set expectations without contradicting 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?
The description is a single, information-dense sentence prefixed by [DRILL-DOWN], followed by a short caveat. Every phrase adds value: the metric, the reference assets, the window, the return type, and the peer comparison. No filler or redundancy.
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 output schema exists and only one parameter is involved, the description covers the essential context: what is computed, over what period, and the statistical caveat. It lacks only explicit parameter format details, which is a minor gap for such a simple 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 0% and the description only implies the 'coin' parameter is the subject, without specifying format (e.g., symbol, name, or ID) or providing examples. The description partially compensates by stating the tool operates on a coin, but not enough to fully define the parameter's semantics.
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 returns correlation and beta of a coin to BTC and ETH with a specific time window and return type, plus correlated peers. This distinguishes it from sibling tools like get_cross_asset_flows and get_market_analogs, which focus on different analytical angles.
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 [DRILL-DOWN] prefix signals this is for in-depth analysis of a specific coin, providing clear context for when to use it. However, it does not explicitly mention alternatives or exclusion criteria, so it stops short of full usage guidance.
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 distinct purposes, but a few pairs like get_liquidation_map vs get_liquidity_map and multiple signal-fetching tools (get_signal, get_signals_since, list_signals, get_actionable_signals) could be confused without careful description reading. Overall, each tool has a clearly defined role, so the ambiguity is limited.
The naming is overwhelmingly consistent: snake_case verb_noun patterns like get_price, list_signals, close_trade, and amend_trade. The exception is 'health' as a plain noun, and a few compound verbs like find_similar_signals, but the overall pattern is strictly followed.
With 52 tools, this is far beyond the typical well-scoped range and falls into the 'too many' category. The broad platform scope justifies many tools, but the sheer number makes the set heavy and harder for an agent to navigate efficiently.
The surface covers the full lifecycle: journal management (log, amend, close, void, read), trade vetting (check, plan, rank), signal discovery (list, get, actionable, similar), market data (price, levels, indicators, options), context (macro, liquidity, flows), forensics (manipulation, trust, narrative), and meta (playbook, usage, health). No obvious gaps or dead ends.