Skip to main content
Glama

invest-like: Buffett-style stock analysis

Find stocks by a rule

find_stocks
Read-onlyIdempotent

Use this when the user asks for stock ideas or a list by a rule: stocks that meet an investor's published rules (rulebook: buffett (Warren Buffett), munger (Charlie Munger), graham (Benjamin Graham), fisher (Philip Fisher), lynch (Peter Lynch), greenblatt (Joel Greenblatt), smith (Terry Smith)), one of invest-like's published daily lists (list), or number filters such as P/E below 15, net margin above 20%, dividend yield above 3%, sales growth above 10%, with an optional sector, country and halal-only. Use exactly one of rulebook, list or filters. Lists come only from invest-like's data, never from memory. Results are screen results, not recommendations.

Input Schema

NameRequiredDescriptionDefault
listNoOne of invest-like's published lists: strongest-moat, highest-roic, cheapest-pe, cheapest-peg, highest-fcf-yield, safest-dividend, lowest-debt, highest-gross-margin, highest-buyback-yield, halal-top-picks, magic-formula-top-30, consistent-compounders
sortNoFor filters: the figure to sort by (default market value)
limitNoHow many to show (default 10)
orderNo
sectorNo
countryNoTwo-letter country code, e.g. US, DE, GB
filtersNo
rulebookNoStocks that meet this investor's published rules, e.g. 'graham' for 'stocks that pass Benjamin Graham's rules'
halal_onlyNoOnly stocks that pass the halal screen

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
      +  "description": "Two-letter country code, e.g. US, DE, GB",
      +  "maxLength": 2,
      +  "minLength": 2,
      +  "type": "string"
      +}
    • addedInput schema / properties / filters
      Added value: +{
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "metric": {
      +        "enum": [
      +          "market_value",
      +          "pe",
      +          "net_margin",
      +          "gross_margin",
      +          "sales_growth",
      +          "return_on_capital",
      +          "dividend_yield",
      +          "net_debt_to_ebitda",
      +          "return_1y"
      +        ],
      +        "type": "string"
      +      },
      +      "op": {
      +        "enum": [
      +          "above",
      +          "below"
      +        ],
      +        "type": "string"
      +      },
      +      "value": {
      +        "description": "Percent metrics in percent (20 = 20%), market value in USD, P/E and net debt / EBITDA as plain numbers",
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "metric",
      +      "op",
      +      "value"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 4,
      +  "type": "array"
      +}
    • addedInput schema / properties / halal_only
      Added value: +{
      +  "description": "Only stocks that pass the halal screen",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"How many to show (default 12)"New value: +"How many to show (default 10)"
    • changedInput schema / properties / limit / maximum
      Previous value: -30New value: +20
    • changedInput schema / properties / list / description
      Previous value: -"Which ranking: strongest-moat, highest-roic, cheapest-pe, cheapest-peg, highest-fcf-yield, safest-dividend, lowest-debt, highest-gross-margin, highest-buyback-yield, halal-top-picks, magic-formula-top-30, consistent-compounders"New value: +"One of invest-like's published lists: strongest-moat, highest-roic, cheapest-pe, cheapest-peg, highest-fcf-yield, safest-dividend, lowest-debt, highest-gross-margin, highest-buyback-yield, halal-top-picks, magic-formula-top-30, consistent-compounders"
    • addedInput schema / properties / order
      Added value: +{
      +  "enum": [
      +    "highest",
      +    "lowest"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / rulebook
      Added value: +{
      +  "description": "Stocks that meet this investor's published rules, e.g. 'graham' for 'stocks that pass Benjamin Graham's rules'",
      +  "enum": [
      +    "buffett",
      +    "munger",
      +    "graham",
      +    "fisher",
      +    "lynch",
      +    "greenblatt",
      +    "smith"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / sector
      Added value: +{
      +  "enum": [
      +    "technology",
      +    "financials",
      +    "healthcare",
      +    "consumer-staples",
      +    "consumer-discretionary",
      +    "communication-services",
      +    "industrials",
      +    "energy",
      +    "utilities",
      +    "real-estate",
      +    "materials"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / sort
      Added value: +{
      +  "description": "For filters: the figure to sort by (default market value)",
      +  "enum": [
      +    "market_value",
      +    "pe",
      +    "net_margin",
      +    "gross_margin",
      +    "sales_growth",
      +    "return_on_capital",
      +    "dividend_yield",
      +    "net_debt_to_ebitda",
      +    "return_1y"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "list"
      -]
  2. Changed6 schema fields changed
    • removedInput schema / properties / investor
      Removed value: -{
      -  "description": "Set when the user asks about one investor, e.g. 'buffett'",
      -  "enum": [
      -    "buffett",
      -    "munger",
      -    "graham",
      -    "fisher",
      -    "lynch",
      -    "greenblatt",
      -    "smith"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / properties / list
      Added value: +{
      +  "description": "Which ranking: strongest-moat, highest-roic, cheapest-pe, cheapest-peg, highest-fcf-yield, safest-dividend, lowest-debt, highest-gross-margin, highest-buyback-yield, halal-top-picks, magic-formula-top-30, consistent-compounders",
      +  "enum": [
      +    "highest-roic",
      +    "cheapest-pe",
      +    "highest-fcf-yield",
      +    "safest-dividend",
      +    "strongest-moat",
      +    "lowest-debt",
      +    "highest-gross-margin",
      +    "cheapest-peg",
      +    "highest-buyback-yield",
      +    "halal-top-picks",
      +    "magic-formula-top-30",
      +    "consistent-compounders"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / min_investors
      Removed value: -{
      -  "description": "Only when no investor is named: minimum of the 7 who would buy. Leave empty for the default (5).",
      -  "maximum": 7,
      -  "minimum": 1,
      -  "type": "integer"
      -}
    • removedInput schema / properties / sector
      Removed value: -{
      -  "description": "Optional sector, e.g. 'Technology', 'Healthcare', 'Financial'",
      -  "maxLength": 40,
      -  "type": "string"
      -}
    • removedInput schema / properties / universe
      Removed value: -{
      -  "description": "sp500 (default), us, or global",
      -  "enum": [
      -    "sp500",
      -    "us",
      -    "global"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / required
      Added value: +[
      +  "list"
      +]
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare a safe, idempotent, closed-world read, so the description's added value is the provenance constraint and the caveat 'Results are screen results, not recommendations' — a genuinely useful expectation-setting statement. It does not say what happens on violating the exactly-one rule or what a result record looks like, keeping it below 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.

Conciseness4/5

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

Front-loaded with the trigger condition and mutual-exclusion rule, followed by compact mode descriptions and a disclaimer. The parenthetical rulebook enumeration is dense but every clause carries routing or unit information; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter, all-optional screening tool with no output schema, the description covers the three mutually exclusive modes, filter units, optional narrowing dimensions, and result framing. It stops short of describing result contents or pagination/limit behavior, which matters given no output schema.

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 67%, and the description compensates by expanding each rulebook enum value with the investor's full name and by giving concrete filter examples with units ('P/E below 15, net margin above 20%', 'sales growth above 10%'). It leaves sort, order, and limit unmentioned, which the schema partially covers.

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?

Opens with a specific verb+resource plus the triggering condition ('stock ideas or a list by a rule'), then enumerates the three screening modes (rulebook, list, filters). The 'list of stocks' framing implicitly separates it from single-stock siblings like check_rulebook and check_value.

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?

Gives explicit when-to-use ('user asks for stock ideas'), an explicit operating constraint ('Use exactly one of rulebook, list or filters'), and a data-provenance rule ('Lists come only from invest-like's data, never from memory'). It also conveys the semantics of what each mode returns.

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