Skip to main content
Glama

Compare stocks

compare_stocks
Read-onlyIdempotent

StockMap's published calls on two to five US stocks side by side, the same for every reader, by symbol or company name: each stock's nightly 14-day read (a call or a lean), whether it changed last night, the insights for and against it, and how the model's past calls on it did. Use it when someone asks how two to five US stocks stack up against each other, or which of them the model's calls read stronger. Each answer carries the not-advice line and the run date.

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": {
      "stocks": "<stocks>"
    },
    "name": "compare_stocks"
  }
}

Input Schema

NameRequiredDescriptionDefault
stocksYesTwo to five US stocks, each by symbol (NVDA, BRK.B) or company name (Nvidia)

Output Schema

NameRequiredDescriptionDefault
runYes
coversYesHow many stocks StockMap calls
missedNo
stocksYesIn the order asked, each once
queriesYes
not_adviceNoThe model's track-recorded read, not financial advice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / $defs / Record / properties / chance / description
      Previous value: -"What a blind call on the same dates scored, a market number (never this stock's percentage); null without a base rate"New value: +"What a random call on the same dates scored, a market number (never this stock's percentage); null without a base rate"
  2. Changed3 schema fields changed
    • addedOutput schema / $defs / Price / properties / price
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Price"
      +}
    • addedOutput schema / $defs / Price / properties / state
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "State"
      +}
    • addedOutput schema / $defs / Price / properties / time
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Time"
      +}
  3. Changed8 schema fields changed
    • removedOutput schema / $defs / LastCall / properties / actual_delta
      Removed value: -{
      -  "description": "How far the stock moved against the index over the window, in points",
      -  "title": "Actual Delta",
      -  "type": "number"
      -}
    • changedOutput schema / $defs / LastCall / required
      Previous value: -[
      -  "date",
      -  "called",
      -  "actual_delta",
      -  "verdict"
      -]New value: +[
      +  "date",
      +  "called",
      +  "verdict"
      +]
    • addedOutput schema / $defs / Record / properties / chance
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "What a blind call on the same dates scored, a market number (never this stock's percentage); null without a base rate",
      +  "title": "Chance"
      +}
    • addedOutput schema / $defs / Record / properties / graded / description
      Added value: +"Independent two-week windows graded"
    • addedOutput schema / $defs / Record / properties / last_line
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The last graded call, as a sentence",
      +  "title": "Last Line"
      +}
    • addedOutput schema / $defs / Record / properties / line
      Added value: +{
      +  "default": "",
      +  "description": "The record line alone: 'Right in h of k two-week windows on SYM since ... (as of ...).', or the too-few line",
      +  "title": "Line",
      +  "type": "string"
      +}
    • changedOutput schema / $defs / Record / properties / text / description
      Previous value: -"The model's record on this stock, as the stock page says it"New value: +"The model's record on this stock, as the stock page says it: the counts of two-week windows and the chance line, or the too-few line"
    • changedOutput schema / $defs / Record / properties / too_few / description
      Previous value: -"True: too few graded calls to judge yet, so no rate is given"New value: +"True: too few two-week windows graded to judge yet, so no record is given"
  4. First observed

TDQS

A4.4/5.0
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, closed-world), yet the description adds real behavior: output is identical for every reader (no personalization), data refreshes nightly as a 14-day read, results include the run date, and every answer carries a not-advice disclaimer.

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?

Two sentences, front-loaded with the core comparison capability and then the usage trigger. The middle enumeration of result contents is dense but informative; nothing is genuinely redundant, though the single long clause could be split for scanability.

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?

One required parameter, full schema coverage, and an output schema means return shape needn't be explained, yet the description still previews result contents, freshness, and the disclaimer. Nothing an agent needs to call or describe this tool correctly is missing.

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 coverage is 100% and the schema already explains the stocks array, the two-to-five bound, and the symbol-or-company-name formats with examples. The description restates the same bounds and identifier forms without adding syntax or error-handling detail, so the schema is doing the work.

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?

States a specific verb and resource ('published calls on two to five US stocks side by side') and enumerates what each result contains: nightly 14-day read, whether it changed, insights for/against, and track record. The two-to-five scope plus the 'same for every reader' framing clearly separates it from the single-stock sibling stock_call.

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?

Explicitly gives a when-to-use trigger: 'when someone asks how two to five US stocks stack up against each other, or which of them the model's calls read stronger.' No when-not conditions or named alternatives (e.g., that a single-stock question belongs to stock_call), so it stops short of full routing guidance.

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