EL7.AI

Strategy baskets

el7_strategy_baskets

Read-onlyIdempotent

The strategy basket library: portfolios of legs ranked by level then yearly return over drawdown, with profit factor, drawdown, trades and out-of-sample re-pick years. Filter by shape, level or strategy slug. In-sample history. One basket: el7_strategy_basket. Single strategies: el7_strategies_list.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "el7_strategy_baskets"
  }
}

Input Schema

Name	Required	Description	Default
`lang`	No	Output language: 'en' (default) or 'ar' for EL7's stored Arabic text.
`limit`	No	Rows to return (max 50).
`shape`	No	'markets' = one strategy across several markets, 'strategies' = several strategies on one market, 'mixed' = both.	markets
`offset`	No	Rows to skip, for paging.
`min_level`	No	Minimum level: 1 = backtest only or better, 2 = held up after the pick.
`strategy_slug`	No	Only baskets that include this strategy as a leg (slug from el7_strategies_list).

Output Schema

Name	Required	Description
`note`	Yes
`as_of`	No	Source freshness: the newest source timestamp behind this result, or null when none is verified. Never request time.
`items`	Yes
`has_more`	Yes
`total_matching`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that by disclosing the result ordering and the 'in-sample history' caveat plus 'out-of-sample re-pick years', which signals survivorship/overfitting context. It does not, however, say how paging interacts with ranking or how large the library is, leaving moderate gaps.

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

Conciseness4/5

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

Dense and front-loaded: identity and ranking rule first, filters second, sibling routing last, with no redundant sentences. It is telegraphic to the point of near-fragments ('In-sample history.'), which costs a little readability but wastes no words.

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

Completeness4/5

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

With an output schema present and full param coverage, the description only needs to supply framing and it does: what a basket is, how results are ordered, what metrics appear, what the in-sample caveat means, and which sibling to use instead. Only minor gaps remain around paging behavior and library scope.

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

Parameters3/5

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

Schema description coverage is 100%, so parameter meaning is already fully carried by the schema; the baseline of 3 applies. The description reinforces that shape, level and slug are the filter axes and that 'level' drives both ranking and filtering, but adds nothing about lang, limit or offset beyond what the schema states.

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 names a specific resource ('the strategy basket library: portfolios of legs') and specifies the ranking rule (level, then yearly return over drawdown) plus the metrics carried. It explicitly distinguishes itself from two similarly named siblings, el7_strategy_basket (single basket) and el7_strategies_list (single strategies), so an agent can separate them without opening schemas.

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

Usage Guidelines4/5

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

It routes the agent clearly: use el7_strategy_basket for one basket and el7_strategies_list for individual strategies, and it names the filter dims ('shape, level or strategy slug'). What is missing is an explicit when-not or prerequisite condition (e.g., that baskets are curated picks rather than a general screener), so it stops short of the top tier.

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

All EL7.AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?