Skip to main content
Glama

Mastering Financial Markets

Read one whole MFM market (open data)

market_series
Read-onlyIdempotent

Read in ONE request every aggregated series MFM publishes for one market, from the open data (free to download, also as CSV at /open-data/): the basket of Observatory companies of the index (price on base 100 at its first month, prices only; basket_gap = basket price ÷ its bottom-up long-term part − 1, same companies on both sides), the Market Weather month by month (grade, family readings, company aggregates) and, for the United States, the S&P 500 sector gaps. Markets with a basket: US (S&P 500), EU (STOXX Europe 600), JP (Japan), CH (Switzerland); other Weather markets have only the Weather series. No company page and no quota consumed. The top-down series (value from the top, its gap, the band) and index levels are not included (licensed inputs). Optional since=YYYY-MM shortens the series; include chooses the blocks. Past data only: no forecast, no expected return, no advice. Clients that only expose search and fetch: search "market: US" or fetch the id "market:US".

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": {
      "market": "<market>"
    },
    "name": "market_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNoOptional first month (YYYY-MM) of the rows returned; default: the whole series.
marketYesMarket code (US, EU, JP, CH, CA, DE, FR, GB, IT) or a name such as "S&P 500", "STOXX Europe 600", "Japan", "Switzerland".
includeNoOptional blocks to return (basket, weather, sectors); default: all the blocks of the market.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses several behavioral facts an agent could not infer: no quota consumed, no company page created, open-data licensing so licensed top-down series and index levels are absent, past-data-only with no forecast or advice, and the CSV mirror at /open-data/. This is substantial added context over the annotation set.

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 with the core action and 'ONE request', which is good, but the bulk is a single sprawling sentence dense with parentheticals (basket_gap definition, market list, licensing notes) that makes it hard to scan. The information mostly earns its place, but the packing hurts readability.

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

Completeness4/5

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

For a bulk read with no output schema, it does the necessary work: describing the blocks returned, which markets have which blocks, licensing exclusions, and the quota cost. The exact shape of the returned payload (per-block structure, row granularity) is only loosely sketched, which is the remaining gap.

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 description coverage is 100%, so the baseline is 3; the description nevertheless adds meaning by explaining that since 'shortens the series' and include 'chooses the blocks', and by clarifying that the default is all blocks of that market and that non-basket markets only have the Weather series. It does not add format or edge-case detail beyond that.

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 with exact scope: 'Read in ONE request every aggregated series MFM publishes for one market'. It enumerates the returned blocks (basket, Market Weather, US sector gaps) and names the markets that have a basket, so an agent can tell immediately this is a whole-market bulk read rather than a company-level call.

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?

Gives clear usage context: it applies to markets in the list, optionally narrowed by since/include, and explicitly routes search/fetch-only clients to `search "market: US"` or id `market:US`. It also states what it deliberately excludes (top-down series, index levels) and that no quota is consumed, though it never contrasts itself against named sibling analytics tools like accumulation_plan or long_term_calculator.

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