Skip to main content
Glama

NS Pros MCP Gateway

nsi-bg__company_facts

TYPED, DETERMINISTIC financial facts for a US public company for an EXPLICITLY NAMED reporting period, "Apple revenue for fiscal 2023", "Walmart net income FY2026 Q3", "Microsoft cash at the end of fiscal 2024". PREFER OVER entity_profile / get_company_financials whenever the period matters: those answer "the most recent figures" and will happily hand back FY2025 when you asked about FY2019, and neither separates a discrete quarter from a year-to-date figure. This one refuses instead, it NEVER s

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": {
      "period": {
        "type": "annual",
        "fiscal_year": 2023
      },
      "company": "AAPL",
      "attribute": "revenue"
    },
    "name": "nsi-bg__company_facts"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoPast ISO timestamp with timezone. Replay the latest answer actually recorded by that instant; no invented history or live fallback.
basisNoOnly "consolidated" in v1. Segment and product-level figures are XBRL-dimensioned and are not reachable through this contract at any concept.
periodYesThe reporting period, stated explicitly. There is no default and no "latest", that is the point of this tool.
companyYesTicker ("AAPL"), 10-digit CIK ("0000320193"), or company name. A name that matches two filers equally well returns status "ambiguous" with both named rather than guessing, pass a ticker or CIK to be certain.
max_ageNoMaximum age in seconds of the upstream publication, not our fetch. Older or undated facts are withheld.
attributeYesWhich figure. "revenue" = total consolidated revenue; "net_income" = net income (loss); "cash" = cash and cash equivalents at the period end; "gross_profit"; "operating_income"; "eps_diluted" (diluted EPS, unit USD/shares, never derived or summed); "capex" (cash paid for PP&E); "operating_cash_flow" (net cash from operating activities); "long_term_debt" (the noncurrent balance-sheet line where the filer tags it, else total long-term debt, `fact.measure` says which); "shares_outstanding" (dei cover-page common shares, unit "shares", as of the COVER DATE rather than the period end).
freshnessNocached (default) permits an eligible stored answer; fresh requires an upstream refresh and never silently falls back to stale data.
restatementNoDefault "as_amended", the latest filed figure for the period, with everything it superseded listed. "as_originally_reported" takes the first filing instead.
exclude_publishersNoPublisher ids forbidden for fact retrieval: sec, fmp, alphavantage. Case and surrounding whitespace are normalized; unknown ids are refused. Excluding sec currently leaves no eligible fact source and returns unavailable/sources_excluded with the selection reasons. Identity and fiscal-calendar lookups may still use SEC; no excluded financial concept is fetched.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

No annotations, so the description must carry behavioral weight, and it does: it discloses that the tool refuses rather than guesses, never falls back to stale/uninvented history, and names ambiguous/unavailable statuses. It stops short of describing the returned fact shape or the full refusal taxonomy (the sentence is cut off at 'it NEVER s'), leaving some burden on the schema.

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 claim and the disambiguation rule before any elaboration, and nearly every clause earns its place. The all-caps emphasis is heavy-handed and the text is truncated mid-sentence, which costs it a point.

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

Completeness3/5

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

For a 9-parameter, nested-schema tool with no annotations and no output schema, the definition covers when-to-use and refusal behavior well. It does not describe what a successful response contains or how refusals are surfaced beyond the status names embedded in the schema, and the truncated ending leaves a disclosure incomplete.

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 property descriptions already explain period, as_of, restatement, freshness, and exclude_publishers semantics in detail. The description adds illustrative natural-language phrasings that map to the parameter structure but no meaning beyond what the schema states, so baseline 3 is right.

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+resource (typed, deterministic financial facts for a named reporting period) and pins the scope to US public companies with an explicitly named period. The contrast with entity_profile / get_company_financials makes it unmistakable which tool returns period-anchored facts versus 'most recent' figures.

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?

Explicitly tells the agent to prefer this tool over two named alternatives whenever the period matters, and explains the exact failure mode of those alternatives (returning FY2025 for an FY2019 question, conflating discrete quarters with YTD). Ambiguity handling is also routed: pass a ticker or CIK instead of a 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.