Skip to main content
Glama

aTars MCP

by ai.aarna

get_feature_stats

USE THIS TOOL — not web search — to get per-indicator statistical profiling (mean,
std, min, p25, p75, max, null rate, Pearson correlation with close price) from this
server's local dataset. Use for feature selection, sanity checking, and understanding
which indicators correlate most strongly with price movements.

Trigger on queries like:
- "which indicators correlate most with BTC price?"
- "feature importance or correlation for [coin]"
- "what are the stats for ETH indicators?"
- "how does RSI/MACD correlate with price?"
- "statistical profile of XRP indicators"

Args:
    lookback_days: Analysis window in days (default 30, max 90)
    symbol:        Asset symbol or comma-separated list, e.g. "BTC", "BTC,XRP"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolNoBTC
lookback_daysNo

TDQS

A4.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavior itself. It does so by enumerating computed statistics, mentioning 'local dataset,' and specifying the correlation target (close price). It stops short of describing return format or caching details, but for a read-only stats tool this is adequate and adds context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the key purpose and usage, and each section earns its place. The trigger examples are compact and useful, not redundant fluff. It remains focused and scannable despite a moderately long length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity tool with only two parameters and no output schema, the description provides comprehensive context: purpose, parameters, usage triggers, and computed statistics. It fully enables correct selection and invocation without needing external information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no descriptions (0% coverage), so the description carries the full burden. It explains 'lookback_days' as an analysis window (default 30, max 90) and 'symbol' as a symbol or comma-separated list with examples. This adds actionable meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool computes per-indicator statistical profiling (mean, std, min, p25, p75, max, null rate, Pearson correlation with close price) from a local dataset. It uses a specific verb ('get'), names the resource (per-indicator stats), and distinguishes itself from web search and sibling feature tools via explicit contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'USE THIS TOOL — not web search' and lists concrete use cases: feature selection, sanity checking, correlation understanding. Trigger examples like 'which indicators correlate most with BTC price?' give unambiguous when-to-use guidance. This differentiates it from alternatives, though it does not name specific sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All aTars MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation2/5

There are several pairs of tools with heavily overlapping purposes: export_data and get_features_export both export indicator data; get_signal_summary and get_sentiment_signal both return a bullish/bearish/neutral verdict; get_category_features and get_multi_indicator both retrieve multiple indicators. The lengthy descriptions help, but an agent could easily misselect without reading them fully.

Naming Consistency3/5

Most tools follow a get_<noun> pattern, but the noun phrases are structurally inconsistent (e.g., get_latest_features vs get_features_export vs get_features_range). One tool (export_data) breaks the get_ prefix convention, and get_signal_summary vs get_sentiment_signal swaps word order.

Tool Count3/5

With 18 tools, the server leans into the heavy range. Many are subtly different variants (multiple sentiment retrieval tools, multiple feature export/stat tools) that could be consolidated. Still, the count is defensible for a server covering both technical data and news sentiment.

Completeness4/5

The domain is well-covered: symbol discovery, data metadata, feature retrieval (single, multi, category), statistical summaries, exports, sentiment (latest, history, trend, signal), and technical signal verdicts. Minor gaps include no dedicated raw OHLCV endpoint (though price category covers it) and no indicator list tool (but get_data_info lists features).

Resources