Skip to main content
Glama

Market Eyes Live - stock ratings and mortgage-rate context

Get the public graded record

get_track_record
Read-onlyIdempotent

Returns the Market Eyes Live public forward-testing record: since when ratings have been captured and graded, how many calls, tickers and graded outcomes, and for each published tier (Favorable and Highest Conviction are recorded together as one favorable tier; Hold; Unfavorable; Rising Star, Very Promising, Promising; Runner!; Catalyst Watch) the share of calls that beat more than half of the other core stocks rated the same day over the next day, week and month, with the calls behind each figure and the 50% no skill line, plus the same against same day core stocks in the same industry where published. Use this when the person asks how accurate or how tested Market Eyes Live ratings are, for example 'what is Market Eyes Live's track record' or 'how often are its favorable ratings right'. Do not use for a single ticker's rating (check_trade carries the record for its tier). Limitations: read from the public feed at https://marketeyeslive.com/api/validation-status, which publishes a cell only once it holds 20 graded outcomes across 8 tickers; a copy is cached for up to 15 minutes and rebuilt on the next read after that, and an older copy, up to about a day old, may answer while a new one builds or while the feed cannot be read (the result carries its last capture date); captures are immutable and grading is automatic. Method: https://marketeyeslive.com/how-melany-is-tested.html. Research data, not financial advice; past results do not guarantee future results; read-only.

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": "get_track_record"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
noteNo
linksNo
sinceYes
tiersYes
sourceYes
tickersNo
headlineNothe favorable tier at one month, in one sentence
raw_feedYes
benchmarkYes
disclaimerYes
capture_daysNo
last_captureNo
no_skill_lineYes
calls_capturedNo
graded_outcomesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), yet the description adds substantial behavioral context: the publishing threshold (a cell appears only at 20 graded outcomes across 8 tickers), a 15-minute cache with rebuild-on-next-read, the possibility of serving a copy up to about a day old including while the upstream feed is unreadable, and that captures are immutable with automatic grading. Those are real operational caveats an agent needs when a user asks about freshness. It stops short of saying how a partially populated or day-old result is signaled in the payload beyond "carries its last capture date," which is why it is not a 5.

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

Conciseness3/5

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

The information is front-loaded and every clause is substantive, but it is delivered as one enormous run-on sentence, with a dense parenthetical listing seven tier names mid-sentence that is hard to parse in one pass. Splitting the usage/exclusion, limitations and method note into separate short sentences would preserve the content and cut reading effort. There is also a stray artifact in the method link ("how-melany-is-tested.html") that reads as a copy error.

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 not required, and the description nonetheless explains the shape of the record, the comparison baseline ("core stocks rated the same day", plus the industry variant where published), the value of the 50% no-skill line, the data source URL, caching/staleness limits and the read-only research disclaimer. For a zero-parameter aggregate-read tool this is fully sufficient to call 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; a 4 baseline is appropriate. The description correctly implies no input is needed by framing the call as reading a single published feed.

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 opens with a specific verb and resource: "Returns the Market Eyes Live public forward-testing record," then enumerates exactly what that record contains (capture start date, call/ticker/outcome counts, per-tier beat-rate over next day/week/month, the 50% no-skill line). It is clearly a public aggregate record, not a per-stock lookup, which separates it from check_trade and get_stock_rating.

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 the triggering user intent with two verbatim example questions ("what is Market Eyes Live's track record", "how often are its favorable ratings right") and an explicit exclusion: "Do not use for a single ticker's rating (check_trade carries the record for its tier)." That is when-to-use, when-not-to-use and the named alternative in one place.

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.