Skip to main content
Glama

get_index_historical

Read-onlyIdempotent

Daily OHLC price history for a major market index, covering the whole date range you ask for.

Chart-ready: while the range fits in one response, each row is the price feed's
own daily row — {symbol, date, open, high, low, close, volume, change,
changePercent, vwap} — newest first, ordered for direct plotting as an index history.

A range too long to return day by day is aggregated into coarser OHLC bars
rather than cut short. `interval` names which (weekly/monthly/quarterly/yearly),
each bar spans `date` to `endDate`, and a bar's high/low are that period's real
extremes. Aggregated bars carry the same fields except `vwap`, which the feed
defines per session only. Re-request a narrower from_date/to_date for daily rows.

`summary` always describes the FULL requested window, computed from the daily
data: its first and last close with dates, its high and low with dates, and the
trailing changes the window reaches back far enough to support. Base any
"starting level", "a year ago" or "period high/low" claim on `summary`, or on a
bar that is actually present.

`summary.windowHigh`/`windowLow` describe THIS window. A quote tool's
yearHigh/yearLow are the feed's trailing range, roughly the past 12-13
months — a different period — so label those as trailing-year figures. For the current level alone, call get_index_quote.

Takes the same index symbols and broker/CFD-name mapping as
get_index_quote — e.g. ^NDX for 'US Tech 100' / 'Nasdaq 100', ^IXIC for
'Nasdaq Composite', ^GDAXI for 'Germany 40'.

Args:
    symbol: Index symbol (e.g. '^GSPC' for S&P 500)
    from_date: Start date YYYY-MM-DD
    to_date: End date YYYY-MM-DD (defaults to today)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYesIndex symbol, e.g. '^GSPC' for the S&P 500.
to_dateNo
from_dateYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "result": {
      -      "title": "Result",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "result"
      -  ],
      -  "title": "get_index_historicalOutput",
      -  "type": "object"
      -}New value: +null
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), but the description adds substantial behavior beyond them: long ranges are aggregated into coarser bars rather than truncated, aggregated bars omit vwap, rows come newest-first, and summary always spans the full requested window. These are non-obvious response-shaping behaviors that materially affect interpretation.

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 purpose and organized into purposeful paragraphs, with the routing hint placed at the end. It is on the long side and repeats the symbol-mapping point already implied, but virtually every sentence carries operational information rather than filler.

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?

With no output schema, the description fully carries the return-shape burden: field list, ordering, aggregation fallback, which fields survive aggregation, and summary semantics. An agent has everything needed to call it and correctly interpret the result.

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 only 33% (from_date and to_date have no schema descriptions), so the description must compensate — and it does, supplying YYYY-MM-DD formats, the 'to_date defaults to today' default, and concrete symbol examples (^GSPC, ^NDX, ^GDAXI). It does not clarify the boundary inclusivity of the range or the interval control it references.

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+scope: 'Daily OHLC price history for a major market index, covering the whole date range you ask for.' It also explicitly names the sibling it is not (get_index_quote) for the current-level case, so an agent can distinguish it without opening either schema.

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 routing: 'For the current level alone, call get_index_quote', and states the remedy for oversized ranges ('Re-request a narrower from_date/to_date for daily rows'). It also tells the agent which construct to base claims on (summary or a present bar) versus the trailing-year figures a quote tool 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