Skip to main content
Glama

Market Eyes Live - stock ratings and mortgage-rate context

Compare stocks

compare_stocks
Read-onlyIdempotent

Lines up 2 to 5 U.S.-listed stocks or ETFs side by side on Market Eyes Live MELANY ratings: conviction tier (weakest to strongest: Unfavorable, Hold, Favorable, Highest Conviction), 0 to 100 composite score, and the valuation, quality and momentum factor scores. Use this when the user wants several tickers' ratings shown together, for example 'compare AAPL, MSFT and GOOGL on quality and valuation' or 'NVDA vs AMD ratings'. Do not use for real-time quotes, price history, options, crypto, futures, non-U.S. listings, or a personal recommendation. Limitations: draws only on the daily-refreshed rated set; a ticker outside it returns a note instead of scores (get_stock_rating can score a covered ticker live), and a ticker outside U.S.-listed stocks and ETFs returns a not-covered note; it does not return entry zones, alert levels or position sizing (has_trade_plan marks a ticker for which Market Eyes Live has a trade plan; the plan values are part of a Market Eyes Live subscription). Methodology and the graded public record: https://marketeyeslive.com/how-melany-is-tested.html. Research data, not financial advice; this tool is read-only and never places trades.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolsYesU.S. ticker symbols, e.g. ["NVDA","AMD"]

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
linksNo
sourceYes
comparisonYesone row per distinct requested ticker, in input order (BRK.B and BRK-B are one ticker)
disclaimerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / comparison / items / properties / has_trade_plan
      Added value: +{
      +  "description": "present (true) only when Market Eyes Live has a trade plan for this ticker; the plan values are not included",
      +  "type": "boolean"
      +}
  2. Changed9 schema fields changed
    • changedInput schema / properties / symbols / description
      Previous value: -"Ticker symbols, e.g. [\"NVDA\",\"AMD\"]"New value: +"U.S. ticker symbols, e.g. [\"NVDA\",\"AMD\"]"
    • changedOutput schema / properties / comparison / description
      Previous value: -"one row per requested ticker, in input order"New value: +"one row per distinct requested ticker, in input order (BRK.B and BRK-B are one ticker)"
    • removedOutput schema / properties / comparison / items / properties / app
      Removed value: -{
      -  "type": "string"
      -}
    • changedOutput schema / properties / comparison / items / properties / note / description
      Previous value: -"present instead of scores when the ticker is outside the daily set"New value: +"present instead of scores: the ticker is outside the daily-refreshed set, not on the coverage list, not covered, or shares its symbol with a futures contract or coin"
    • changedOutput schema / properties / comparison / items / properties / rating_tier / description
      Previous value: -"User-facing conviction tier, same ladder as get_stock_rating: Unfavorable, Hold, Favorable, Highest Conviction weakest to strongest, with Highest Conviction at a composite of 69 or above. Names without mature fundamentals read Promising, Very Promising or Rising Star instead."New value: +"Conviction tier. Mature ladder, weakest to strongest: Unfavorable, Hold, Favorable, Highest Conviction. Favorable and Highest Conviction are both favorable reads; Highest Conviction is a composite of 69 or above (for a stock, a small hysteresis can hold a borderline label steady between refreshes; a fund or REIT word follows its label in the app, which has none). Names the mature ladder does not cover carry their own label: Promising, then Very Promising, then Rising Star for names without mature fundamentals, Runner! for a momentum surge, Catalyst Watch for a news-driven gap up on volume. ETFs and REITs use the same mature ladder, chosen by the tone of the fund's own label in the app (a favorable fund label reads Favorable or Highest Conviction, a cautious or neutral one Hold, a negative one Unfavorable); a leveraged or inverse fund never reads above Hold. These nine words are the complete set; null when no tier applies."
    • addedOutput schema / properties / disclaimer
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / links
      Added value: +{
      +  "properties": {
      +    "methodology": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / source
      Added value: +{
      +  "type": "string"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "comparison"
      -]New value: +[
      +  "comparison",
      +  "source",
      +  "disclaimer"
      +]
  3. Changed1 schema field changed
    • addedOutput schema / properties / comparison / items / properties / app
      Added value: +{
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • addedOutput schema / properties / comparison / items / properties / rating_tier / description
      Added value: +"User-facing conviction tier, same ladder as get_stock_rating: Unfavorable, Hold, Favorable, Highest Conviction weakest to strongest, with Highest Conviction at a composite of 69 or above. Names without mature fundamentals read Promising, Very Promising or Rising Star instead."
  5. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "comparison": {
      +      "description": "one row per requested ticker, in input order",
      +      "items": {
      +        "properties": {
      +          "as_of": {
      +            "type": "string"
      +          },
      +          "company": {
      +            "type": "string"
      +          },
      +          "composite_score": {
      +            "description": "0-100",
      +            "type": "number"
      +          },
      +          "momentum": {
      +            "type": "number"
      +          },
      +          "note": {
      +            "description": "present instead of scores when the ticker is outside the daily set",
      +            "type": "string"
      +          },
      +          "quality": {
      +            "type": "number"
      +          },
      +          "rating_page": {
      +            "type": "string"
      +          },
      +          "rating_tier": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "symbol": {
      +            "type": "string"
      +          },
      +          "valuation": {
      +            "type": "number"
      +          }
      +        },
      +        "required": [
      +          "symbol"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "comparison"
      +  ],
      +  "type": "object"
      +}
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, yet the description adds substantial context beyond them: the daily-refreshed rated-set constraint, the 'not-covered note' fallback for out-of-set or non-U.S. tickers, the absence of entry zones/alert levels/position sizing, and the subscription gating of trade-plan values. It also discloses that a ticker outside the rated set returns a note rather than an error.

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 core purpose, examples, and exclusions are front-loaded in the first two sentences, and the methodology link and disclaimer are correctly deferred to the end. It is dense in a single paragraph and some limitation detail (trade-plan/subscription wording) could be tightened, but nearly every clause carries actionable information.

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?

An output schema exists, so return-value documentation is unnecessary, and the description fills the remaining gaps: coverage limits, fallback behavior for uncovered or non-U.S. tickers, and what the tool deliberately omits. An agent has everything needed to select and invoke it correctly.

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

Parameters4/5

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

Schema coverage is 100% (the single parameter is documented with min/max items and an example), so the baseline is 3. The description exceeds it by specifying the symbol domain: U.S.-listed stocks or ETFs only, with non-U.S. listings falling back to a not-covered note, which the schema does not convey.

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 uses a specific verb and resource ('lines up 2 to 5 U.S.-listed stocks or ETFs side by side on ... MELANY ratings') and enumerates exactly what is compared (conviction tier, composite score, factor scores). It also distinguishes itself from get_stock_rating, which it names as the live-scoring alternative for a single covered ticker.

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 states when to use the tool with concrete example phrasings ('compare AAPL, MSFT and GOOGL on quality and valuation'), gives an explicit do-not-use list (real-time quotes, price history, options, crypto, futures, non-U.S. listings, personal recommendations), and routes to the sibling get_stock_rating for live coverage. This is about as complete as usage guidance gets.

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.