Skip to main content
Glama

Mastering Financial Markets

Read a public MFM record

fetch
Read-onlyIdempotent

Read one numbered part of a published MFM document or dataset (an id returned by search that starts with "portfolio:" recomputes the portfolio calculator, nothing stored). Company metadata includes verification_level, audit_id, audit_url and controls_performed. metadata.next_id identifies the following part or is null. Audit levels describe programme membership. Company records: amounts are whole units of the currency stated in each period (field currency), never thousands or millions; ratios in metrics are decimals (0.15 = 15%) except years_* (years), interest_coverage, cash_conversion, capex_to_depreciation and debt_to_equity* (multiples, 1.5 = 1.5 times). years are in ascending order: the latest fiscal year is the LAST element, in the last parts, so follow every next_id before answering. ttm, quarters and interim_reports are separate periods with their own end dates; latest_interim names the most recent interim period and the block that holds it: use that one and never annualise. A null metric has its reason in warnings of the same period; an absent key is not zero. P1 v3: reason recorded in the source language; see audit (figures in the source: 1; 3); pe.ttm_fine and pe.eps_ttm identify the actual earnings period and EPS. pe.ttm_reason_en explains a missing TTM ratio. Always state both the price date and the earnings period beside every P/E; fiscal-year P/E is not TTM P/E. The pe block holds the P/E shown on the site, with the month-end price, its date and currency, earnings per share and the method (pe_latest null = not computed, reason in reason_en; pe_at_price = P/E on the latest fiscal year closed by the price date, rule P1 in pe.rule, with fiscal_year_at_price and note_en; date_price = date of the month-end price, never before the fiscal year end); other price-based figures (market value, dividend yield) are not in the record. public_float is the aggregate market value of shares held by non-affiliates declared on the cover of the annual report (SEC: at the end of the second fiscal quarter), not the current market capitalisation; public_float_info gives its date, filing and definition. Two rows with the same fiscal_year (change of year-end) are told apart by period_label. When retained_card_en is present, the record is retained and no longer updated by the computation: state since when, why and the last financial year before using its figures. A period with different_scope belongs, wholly or for the listed items (field items), to a different entity (shell, SPAC, reverse-merger predecessor, divested scope): say so, use its en text and do not compare it with later periods. Descriptive data only: no forecast, no recommendation.

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": {
      "id": "<id>"
    },
    "name": "fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesAn id returned by search or list_datasets (company, page or dataset), the metadata.next_id of the previous part, "user-proposal:<id>" for the separate User Register, "quota" for the account allowances, or a "portfolio:" id returned by search. Also "market:US" (one whole market of the open data) or a "plan:" id returned by search.
model_idNoOptional identifier of the model used for the inspection; client-declared, not model attestation.

Output Schema

NameRequiredDescriptionDefault
idYes
urlYes
textYes
titleYes
metadataNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / id / description
      Previous value: -"An id returned by search or list_datasets (company, page or dataset), the metadata.next_id of the previous part, \"user-proposal:<id>\" for the separate User Register, \"quota\" for the account allowances, or a \"portfolio:\" id returned by search."New value: +"An id returned by search or list_datasets (company, page or dataset), the metadata.next_id of the previous part, \"user-proposal:<id>\" for the separate User Register, \"quota\" for the account allowances, or a \"portfolio:\" id returned by search. Also \"market:US\" (one whole market of the open data) or a \"plan:\" id returned by search."
  2. Changed1 schema field changed
    • addedInput schema / properties / id / description
      Added value: +"An id returned by search or list_datasets (company, page or dataset), the metadata.next_id of the previous part, \"user-proposal:<id>\" for the separate User Register, \"quota\" for the account allowances, or a \"portfolio:\" id returned by search."
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare the tool read-only, idempotent and non-destructive. The description adds substantial behavioral context: portfolio ids recompute without storing, metadata.next_id continues parts, null reasons live in warnings, retained/different_scope caveats apply, and P/E and unit conventions are disclosed. Nothing contradicts the annotations.

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?

The purpose is front-loaded, but the remainder is a very dense single paragraph of domain caveats. Many sentences are useful, yet the description is far longer and less scannable than typical tool guidance and would benefit from bullets or moved documentation.

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?

Given a complex financial-data fetch with an output schema and strong annotations, the description covers units, ratio conventions, period ordering, latest interim handling, null semantics, audit fields, P/E rules, public float, retained records and scope changes. It is complete enough for correct 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 id and model_id are already documented in the input schema. The description adds meaning for id by explaining that a portfolio: id recomputes the calculator without storing anything and that next_id should be followed, though it does not elaborate model_id.

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 opening sentence gives a specific verb (Read) and resource (one numbered part of a published MFM document or dataset), and immediately explains the special portfolio-id case. It is broad enough to cover dataset, market, quota, plan and user-proposal ids while making the core fetch behavior unambiguous.

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 supplies operational usage rules: follow every next_id, use latest_interim and never annualise, and state price date and earnings period beside P/E. It gives clear usage context but does not explicitly compare fetch with search or list_datasets, nor state when not to use it.

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