Skip to main content
Glama

Chart of a company's financial history

chart_company_history
Read-onlyIdempotent

Beispiel: „Bilanzsumme, Umsatz und Ergebnis der Red Bull GmbH über die Jahre als Grafik?“

The per-year financial history of ONE company drawn as a chart image (PNG, 1200x600), rendered here: the model shows it inline and never writes HTML. Read-only. Same data, budget and plan rules as get_company_history (the company counts once).

    Parameters:
    - company_id (required): "AT:{fnr}" or "DE:{court}_{type}{number}" (bare national ids
      accepted), from a search card.
    - metrics (optional): the series to draw; default bilanzsumme, eigenkapital,
      umsatzerloese, jahresueberschuss (grouped bars, left) plus equity_ratio, ebit_margin,
      net_margin (lines in per cent, right). German names are accepted (eigenkapitalquote,
      ebit_marge, umsatzrendite); describe_fields lists the rest.
    - years (optional): how many of the most recent financial years to draw (default and
      maximum 8).

    Returns two content blocks: the image, and a text block with the same numbers as a
    Markdown table (newest year right, amounts in T€ or Mio. € chosen by magnitude, ratios
    in %, a dash for a missing year) and the source line with the data state. Values are
    served as they are (expenses and losses negative); a series with fewer than two values
    is named under the chart instead of drawn. With fewer than two financial years in the
    register there is no image, only a text that lists the years found and points to
    get_document for the filing itself. Germany serves the parsed Jahresabschluss where the
    company has filed and its Bundesland is loaded; an empty answer means not filed or not
    loaded, never zero.

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": {
      "company_id": "<company_id>"
    },
    "name": "chart_company_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearsNo
metricsNo
company_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations cover only the safety profile (readOnly, idempotent, closed-world), and the description adds substantial behaviour: exact output dimensions, inline display with no HTML generation, two content blocks (image plus Markdown table), sign conventions for expenses and losses, handling of series with fewer than two values, and Germany-specific data-availability caveats. The closing note that an empty answer means not filed or not loaded rather than zero is exactly the kind of trap-avoidance an agent needs.

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?

The structure is logical and front-loaded: purpose, then parameters, then return behaviour, then edge cases. The leading German sample query is a useful intent cue but sits awkwardly ahead of the core statement and mixes languages with the otherwise English text, slightly delaying the key sentence.

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 rendering tool with no output schema and three undocumented parameters, the description covers everything needed: identity format, metric selection, year limits, the exact shape of both returned blocks, and the degraded paths when data is missing or not loaded. Nothing an agent needs in order to call it correctly or to interpret an empty result is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does so: company_id format is spelled out with both AT and DE patterns plus bare national ids and where to obtain them, metrics documents defaults, the bar-vs-line placement, accepted German aliases, and a pointer to describe_fields, and years states both default and maximum (8). This is meaning the schema alone does not convey.

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?

The first sentence names a specific verb and resource: "The per-year financial history of ONE company drawn as a chart image (PNG, 1200x600)". It distinguishes itself from get_company_history by noting the shared data but different output form, and the capitalised ONE plus the rendering note remove any ambiguity about scope.

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?

The description establishes clear usage context through the opening example (a chart request) and explicit fallback routing: fewer than two financial years means no image, so it points to get_document for the filing. The shared budget note against get_company_history helps an agent choose, though the description never states when to prefer get_company_history or benchmark_company over this chart.

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.