get_oi_divergencePrice-vs-OI regime per coin from our continuous snapshots: NEW_LONGS / SHORT_SQUEEZE / NEW_SHORTS / LONG_LIQUIDATION. Scan all tracked coins or analyze one. Impossible without OI history, which no public API provides — only predmcp records it.
| Name | Required | Description | Default |
|---|---|---|---|
| coin | No | One coin (e.g. "BTC") — omit to scan all tracked coins | |
| hours | No | Lookback window in hours (default 24, max 90d) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the tool is safely read-only with variable output. The description adds that it uses 'continuous snapshots' and relies on OI history unique to predmcp, but does not detail how often snapshots update or how regimes are determined. Behavior is adequately disclosed but not richly detailed.
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 concise sentences: first describes purpose and output categories, second emphasizes data uniqueness. Every word contributes value; no fluff.
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 no output schema, the description lists the four possible regime outputs and explains usage modes. It could specify the return format (e.g., per coin object or list), but for a classification tool, this is sufficiently complete. Minor gap in data structure details.
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%: both 'coin' and 'hours' have descriptions. The description reinforces that 'coin' can be omitted for scanning all coins, but adds no additional meaning beyond the schema. Baseline 3 is appropriate.
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 the tool provides a price-vs-OI regime classification per coin, listing the four output categories (NEW_LONGS, SHORT_SQUEEZE, NEW_SHORTS, LONG_LIQUIDATION) and two usage modes (scan all or one coin). It also distinguishes itself by noting the unique OI history data source, differentiating it from siblings.
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 indicates when to use: for OI divergence regime analysis, with options to scan all tracked coins or analyze a specific one. It implicitly suggests this tool is for specialized OI-based regime detection, but does not explicitly state when not to use or compare to alternative tools like 'get_oi_history' or 'get_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.
Many tools are specialized, but several pairs have fuzzy boundaries: e.g., get_funding_rates vs get_top_funding_rates, get_basic_macro vs get_macro_context, get_simple_iv vs get_options_iv. An agent could easily select the wrong one.
Most tools follow a 'get_X' pattern with descriptive noun phrases. There are a few exceptions like 'create_api_key' and 'search_markets', but overall the convention is consistent and readable.
With 47 tools, the server is overloaded. While the domain is broad, this many tools makes discovery and selection difficult for an agent, reducing coherence.
The tool set covers an impressively wide range: macro data, funding, prediction markets, OI history, whale tracking, risk analytics, position sizing, backtesting, and signal generation. It leaves no obvious gaps for a crypto trading assistant.