Skip to main content
Glama

One ratio as a series (daily for valuation)

ratios_daily
Read-onlyIdempotent

Return one ratio as a series, most recent first. For a valuation ratio (market_cap, enterprise_value, pe_ttm, ps_ttm, pb, ev_ebitda_ttm, ev_ebit_ttm, fcf_yield, dividend_yield) there is one point per trading session: the IEX close of that day times the standardized facts known that evening (trailing twelve months for flows, the latest balance sheet), so a P/E series never uses a filing accepted later. Points are withheld after a split-sized move until split data exists; data.price_basis says which listing was used and why a company is not priced (several share classes such as BRK-A and BRK-B, an ADR, no prices). Each point is a value object whose proof.inputs lists the close first, then the facts; proof_get recomputes it. For a fundamentals ratio (gross_margin, roe, nii_to_avg_loans_securities...) there is one point per fiscal period of period_type. IEX is a single venue and its last trade is not the official close; say so when quoting. Use it for the history of one ratio, such as a P/E series or a margin trend.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 30,
      "company": "ticker:AAPL",
      "ratio_id": "pe_ttm"
    },
    "name": "ratios_daily"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoValuation only: last session date, inclusive (YYYY-MM-DD).
fromNoValuation only: first session date, inclusive (YYYY-MM-DD).
as_ofNoKnowledge date or timestamp (YYYY-MM-DD or RFC 3339). The answer is what FinancialMD knew at that instant: only facts whose known interval contains as_of. Omit for the current view.
limitNoMaximum number of periods or items to return (default 30, at most 1000).
cursorNoOpaque cursor from a previous page (data.next_cursor).
tickerNoValuation only: the listing whose close is used (default the primary listing with bars).
companyYesCompany identifier: a FinancialMD id ("fmd_01H..."), an SEC CIK ("cik:320193"), or a ticker ("ticker:AAPL", optionally with the MIC "ticker:AAPL.XNAS"). A bare ticker like "AAPL" is accepted and sent as ticker:AAPL. An issuer on an EU or UK regulated market that does not file with the SEC has no CIK: pass its LEI ("lei:IOG4E947OATN0KJYSD45") or its fmd_ id.
ratio_idYesRatio id. Valuation ids give a daily series; the others one point per period.
period_typeNoPeriod basis: annual (fiscal years), quarterly, ltm (last twelve months) or ytd (year to date).annual

Output Schema

NameRequiredDescriptionDefault
dataNo{ ratio_id, label, formula, metric_format, period_type ("daily" for valuation), view, items: [value objects], next_cursor, price_basis?: { listing, source, unavailable } }
metaNoRequest metadata: request_id, as_of, company resolution, coverage, pipeline_version, licence, terms, proof_base.
errorNoPresent only on isError results: the API error code and message plus remedy hints.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / company / description
      Previous value: -"Company identifier: a FinancialMD id (\"fmd_01H...\"), an SEC CIK (\"cik:320193\"), or a ticker (\"ticker:AAPL\", optionally with the MIC \"ticker:AAPL.XNAS\"). A bare ticker like \"AAPL\" is accepted and sent as ticker:AAPL."New value: +"Company identifier: a FinancialMD id (\"fmd_01H...\"), an SEC CIK (\"cik:320193\"), or a ticker (\"ticker:AAPL\", optionally with the MIC \"ticker:AAPL.XNAS\"). A bare ticker like \"AAPL\" is accepted and sent as ticker:AAPL. An issuer on an EU or UK regulated market that does not file with the SEC has no CIK: pass its LEI (\"lei:IOG4E947OATN0KJYSD45\") or its fmd_ id."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations: it explains point-in-time knowledge semantics (a P/E series never uses a filing accepted later), discloses that points are withheld after a split-sized move until split data exists, explains data.price_basis including the reasons a company may be unpriced (multiple share classes, ADR, no prices), and warns that IEX is a single venue whose last trade is not the official close. These are exactly the caveats an agent needs to interpret or quote results without misleading a user.

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 core statement, then ordered from valuation mechanics to fundamentals to the caveat and finally the use case. Some sentences are heavily nested (the price_basis sentence in particular) and could be split, but essentially every sentence carries information that is not duplicated elsewhere.

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 structure need not be described; the description instead covers the things the schema cannot — knowledge-date semantics, withholding behavior, listing/price_basis reasoning, and the IEX venue caveat. For a 9-parameter series tool with pagination, this is complete enough for correct invocation and interpretation.

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 100%, so the baseline would be 3, but the description adds genuine meaning: from/to are scoped to valuation series only, ticker selects the listing whose close is used, period_type drives one-point-per-fiscal-period for fundamentals ratios, and as_of is framed as a knowledge cutoff. It also tells the agent the ordering of results (most recent first), which the schema does not state.

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 ("Return one ratio as a series, most recent first") and immediately splits the behavior into two named modes: valuation ratios that yield one point per trading session, and fundamentals ratios that yield one point per fiscal period. This distinguishes it clearly from a point-in-time sibling like ratios and from proof_get, which it explicitly cross-references.

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?

Closes with explicit usage guidance ("Use it for the history of one ratio, such as a P/E series or a margin trend") and names proof_get as the tool for recomputing an individual point, which routes the agent correctly for verification. It does not explicitly say when to prefer a point-in-time or snapshot alternative over a series, leaving that boundary to inference from the name.

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