Skip to main content
Glama

Stock call

stock_call
Read-onlyIdempotent

StockMap's published call on one US stock, the same for every reader, by symbol or company name: the model's nightly 14-day read (a call or a lean), the strongest reasons for and against, how its past calls on the stock did, the price and the day's change, and what changed last night. Use it when someone asks how a US stock looks, whether it reads strong or weak right now, or what the model's read on it is. 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": {
      "stock": "<stock>"
    },
    "name": "stock_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
stockYesA US stock's symbol (NVDA, BRK.B) or its company name (Nvidia)

Output Schema

NameRequiredDescriptionDefault
runYes
queryYes
stockNoNone when no one stock matched
coversYesHow many stocks StockMap calls
closestNoThe stocks the query may have meant
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. Changed1 schema field changed
    • addedOutput schema / $defs / Reason / properties / checked_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "YYYY-MM-DD the rate was last checked (two-week moves)",
      +  "title": "Checked At"
      +}
  3. 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"
      +}
  4. 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"
  5. Changed6 schema fields changed
    • addedOutput schema / $defs / Reason / properties / base_rate
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "How often the same calls would be right by chance; null before the rule's blocks carry the counts",
      +  "title": "Base Rate"
      +}
    • addedOutput schema / $defs / Reason / properties / hit_rate / anyOf
      Added value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / $defs / Reason / properties / hit_rate / default
      Added value: +null
    • removedOutput schema / $defs / Reason / properties / hit_rate / type
      Removed value: -"number"
    • changedOutput schema / $defs / Reason / properties / right / description
      Previous value: -"How often the insight has been right, as the page says it"New value: +"How often the insight has been right beside its base rate, as the page says it; empty when it has no accuracy"
    • changedOutput schema / $defs / Reason / required
      Previous value: -[
      -  "line",
      -  "sentence",
      -  "right",
      -  "hit_rate",
      -  "drivers"
      -]New value: +[
      +  "line",
      +  "sentence",
      +  "right",
      +  "drivers"
      +]
  6. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish a safe, idempotent, read-only, closed-world lookup, so the description isn't burdened with safety disclosure. It adds meaningful behavioral context beyond them: the answer is identical for every reader, is refreshed nightly with a run date, and always carries a not-advice line — all of which shape how an agent relays output.

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?

Purpose and scope come first, followed by a usage sentence and a short output/caveat note — appropriate front-loading with no filler. The first sentence is a long enumerated list, some of which duplicates what the output schema already conveys, costing it a point.

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?

For a one-parameter read tool with full annotation and output-schema coverage, the description supplies everything an agent needs: what is returned, when to invoke it, the nightly/run-date cadence, and the mandatory not-advice framing. Nothing material 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 single required parameter's description already explains symbol or company-name input with examples (NVDA, BRK.B). The description's 'by symbol or company name' restates that rather than adding new semantics such as format tolerance or ambiguity handling, so baseline 3 applies.

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 resource and scope: 'StockMap's published call on one US stock ... by symbol or company name,' then enumerates the payload (nightly 14-day read, reasons for/against, track record, price and change, overnight delta). The 'one US stock' scoping implicitly separates it from market-wide or comparison siblings such as market_map or compare_stocks.

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?

Gives concrete trigger conditions: 'when someone asks how a US stock looks, whether it reads strong or weak right now, or what the model's read on it is.' It lacks explicit exclusions or named alternatives (e.g., use compare_stocks when two tickers are involved), so routing away from siblings is left to inference.

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