Skip to main content
Glama

Stock Expert AI Research

Stock Expert AI: ranked stock screen

stockexpertai_screen_stocks
Read-onlyIdempotent

Return one of Stock Expert AI's ranked lists — the same rows as the site's "Best ... Stocks" pages — for a sector, industry, theme or strategy. Every answer states the exact filter it applied (rankedBy + criteria) so the list can be described accurately.

Cuts (each is a site-wide list; the numeric filter is returned with the rows): best = the scope's list ranked by MoonshotScore · undervalued = P/E ≤ 18, market cap ≥ $1B · dividend = dividend yield 1.5%-12%, market cap ≥ $2B, ranked by yield · high-growth = revenue growth ≥ 15%, market cap ≥ $1B · small-cap = market cap $300M-$2B. Cuts other than "best" are market-wide: a sector or theme scope is not applied to them (scopeApplied=false says so). Scopes for cut=best: the 11 sectors (technology, healthcare, financial, energy, consumer discretionary, industrial, real estate, utilities, materials, communication, consumer staples), themes (ai, semiconductors, ev, renewable energy, cybersecurity, cloud computing, biotech, cannabis, quantum computing, space, robotics, fintech, metaverse, water) and strategies (dividend, growth, value, penny, blue chip, momentum, defensive, small/mid/large cap, low volatility, undervalued, under 10, under 50). Use when: "best semiconductor stocks", "undervalued stocks", "top MoonshotScore stocks in healthcare". Present results as a rated list with the as-of date and the stated criteria, never as picks to buy. Args: scope (string); cut (enum, default "best"); limit (int 1-20, default 10). Returns (structuredContent): { scope, cut, rankedBy, criteria, scopeApplied, asOf, rows: [{ rank, ticker, company, moonshotScore, canonicalUrl }], canonicalUrl, fullFigures, disclaimer }. Rows carry no price, market cap or P/E: full figures on the list page and on each row's stock page. Errors: "No screen for " — the scope is not one of the site's lists; try one of the names above. Derived output only: Stock Expert AI's own ratings, sentences and dates. Raw market figures (price, market cap, P/E, EPS, revenue) are not returned — full figures on the page (canonicalUrl). MoonshotScore is Stock Expert AI's educational research rating, not a buy or sell recommendation. Not financial advice. Not a registered investment adviser.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "scope": "<scope>"
    },
    "name": "stockexpertai_screen_stocks"
  }
}

Input Schema

NameRequiredDescriptionDefault
cutNoWhich listbest
limitNoRows to return (1-20)
scopeYesSector, industry, theme or strategy, e.g. technology, semiconductors, dividend

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond them: the exact numeric filter behind each cut, the fact that rows omit price/market cap/P/E, the structured return shape, the 'No screen for <scope>' error, and a disclaimer that MoonshotScore is an educational rating. That is the kind of context an agent needs to present results accurately rather than as buy recommendations.

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?

The definition is front-loaded and information-dense, with cuts, scopes and returns clearly partitioned. It loses a point for duplication: the 'rows carry no price, market cap or P/E' statement is repeated almost verbatim in the 'Derived output only' paragraph, and the disclaimer is restated twice.

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?

Although there is no output schema, the description fully enumerates the structuredContent fields (scope, cut, rankedBy, criteria, scopeApplied, asOf, rows, canonicalUrl, disclaimer), the error case, and the limitation on raw market figures. For a three-parameter read-only tool this leaves nothing an agent needs in order to call it and describe results correctly.

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?

Schema coverage is 100%, so the baseline would be 3, but the description goes well beyond it by enumerating valid scopes (11 sectors, 13 themes, a dozen strategies) and defining each cut's actual filter thresholds (P/E ≤ 18, market cap ≥ $1B, yield 1.5%-12%, etc.). It also clarifies that limit is rows returned and defaults are cut='best', limit=10, which meaningfully improves invocation accuracy.

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 opening sentence gives a specific verb and resource ('Return one of Stock Expert AI's ranked lists') and pins the scope to a sector, industry, theme or strategy. It also distinguishes the artifact from siblings implicitly by describing a ranked screen rather than a single-stock lookup or comparison, and the 'same rows as the site's Best ... Stocks pages' framing removes ambiguity about what is returned.

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?

Explicit 'Use when' examples ('best semiconductor stocks', 'undervalued stocks', 'top MoonshotScore stocks in healthcare') map directly to the arguments. It also documents a critical routing rule — cuts other than 'best' are market-wide and ignore scope (scopeApplied=false) — and gives error handling for unknown scopes, so the agent knows both when to call it and how to recover from a bad scope.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources