Skip to main content
Glama

The verdict line for one filed move

verdict
Read-only

One guru's disclosed move in one ticker, with the sentence Deep Values publishes about it and every number behind it: the company's legal name beside the ticker (name, null where we hold none), the three dates (traded by, filed, seen), the quarter-end close, the current price, and the intrinsic value band. value is the callable band (the lead value ±25%: Owner Earnings, else the DCF, else Damodaran) and is null whenever the verdict is not a call; estimates always carries what the valuation methods actually said, their lowest and highest central estimate, so a reader told we cannot call it can see why. One of six deterministic states — below_value, inside_band, above_value, ran_ahead, too_uncertain, no_value — computed the same way for every caller. The band is Deep Values' lead intrinsic value (the one the apps headline: Owner Earnings first) plus or minus 25%, and too_uncertain ("Our estimates disagree too much to call this one.") replaces the three band states when the methods' own central estimates are more than 3x apart, or one of them is not positive: the lead value still exists, but value is null because it is not a range anyone should be told a price sits inside; estimates shows how far apart the methods are. It is distinct from no_value, which means no valuation was computed at all. Before the band is published its mid is checked against the current price (positive, at most 20x the price, a price under five days old; under 0.05x is served with the flag iv_far_below_price) and for currency (currency_consistent: the statements behind it are in USD, the price's currency, or were converted to USD; a converted band carries fx on values.value_band_mid naming the original currency and rate; when the currency is not known the answer carries the flag currency_unverified instead); on a failure value and estimates are null, the verdict reads no_value, withheld is true, checks.failed names the check, and the call is not charged. (GET https://app.deepvalues.ai/api/v1/verdict/{ticker}, e.g. https://app.deepvalues.ai/api/v1/verdict/AAPL?guru=warren-buffett — 0.02 credits per call; works with no credentials up to 5 call(s)/day per address) Missing data? Call request_data.

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": {
      "ticker": "<ticker>",
      "guru": "<guru>"
    },
    "name": "verdict"
  }
}

Input Schema

NameRequiredDescriptionDefault
guruYes
tickerYesThe real ticker symbol, e.g. AAPL; share classes as BRK.B or BRK-B. Substitute it into the path (/fundamentals/AAPL), never the literal {ticker}.
quarterNoQuarter end; default = the most recent quarter we hold.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / guru / examples
      Added value: +[
      +  "warren-buffett"
      +]
    • addedInput schema / properties / quarter / examples
      Added value: +[
      +  "2026-06-30"
      +]
    • addedInput schema / properties / ticker / description
      Added value: +"The real ticker symbol, e.g. AAPL; share classes as BRK.B or BRK-B. Substitute it into the path (/fundamentals/AAPL), never the literal {ticker}."
    • addedInput schema / properties / ticker / examples
      Added value: +[
      +  "OXY"
      +]
  2. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only cover readOnlyHint and openWorldHint; the description adds substantial behavior beyond them: credit cost per call, credential-free quota, detailed failure semantics (`value` and `estimates` null, `withheld` true, `checks.failed` names the check, call not charged), the price sanity checks with `iv_far_below_price`, and the currency checks with `fx`/`currency_unverified`. This is exactly the kind of context annotations cannot carry.

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?

It is front-loaded, opening with the return payload, and every clause is substantively about behavior. But it is delivered as one very long, deeply nested paragraph with stacked parentheticals, which makes it hard to scan for the states, checks, and failure rules buried inside.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it does: it enumerates the six states, defines the band construction and the ±25% rule, explains the 3x disagreement threshold, and documents the failure path and flags. For a tool of this complexity, 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 67%, with ticker and quarter already documented in the schema. The description adds only marginal parameter meaning: the example URL shows the `guru` slug format (`warren-buffett`) as a query parameter and reinforces path substitution for the ticker. Most of the description's field-level detail concerns outputs (`name`, `value`, `estimates`), not the three inputs, so it does not lift much above the schema baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource and scope: one guru's disclosed move in one ticker, with a named set of returned fields (name, the three dates, quarter-end close, current price, value, estimates) and six enumerable verdict states. It further distinguishes `too_uncertain` from `no_value`, which sharpens the concept. It does not, however, say how this differs from sibling tools like `intrinsic_value` or `guru_moves`, so an agent still has to infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the exhaustive description of what comes back, and there is one explicit conditional alternative: 'Missing data? Call `request_data`.' Cost (0.02 credits) and credential-free limits (5 calls/day) are also stated. But there is no explicit when-to-use versus `intrinsic_value`, `guru_moves`, or `company_overview`, which is the main gap for an agent choosing among siblings.

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