Skip to main content
Glama

Tapetide - Indian Stock Market MCP

Financial Statements

get_financials
Read-onlyIdempotent

Get financial statements for one company. Sections: quarterly (quarterly P&L), profit_loss (annual P&L), balance_sheet, cash_flow, ratios (all annual). Default: the latest periods with growth rates (quarterly ~13 quarters); omit section for all sections trimmed to 5 periods each (periods widens, e.g. {"symbol":"TCS","section":"quarterly","periods":12}). Each section carries periods (oldest first), data {row: {period: value}}, pct_changes, row_order and availability with each period's point-in-time available_from. LONG HISTORY: pass section with from, to, as_of or basis for a period table (broad from FY2015, sparse before), up to 60 periods per call, newest first; when meta.next_to is set, call again with to = that date for older periods. That table's eps_basis: as_reported, restated or null. as_of returns only what was public then (backtests); values may include later restatements. One symbol per call; to compare companies use get_batch_financials. ETFs, index funds and bonds have no statements.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_financials"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoHistory: latest period end, YYYY-MM-DD (`meta.next_to` for the next page).
fromNoHistory: earliest period end, YYYY-MM-DD.
as_ofNoHistory: only figures public by this date, YYYY-MM-DD.
basisNoHistory: preferred (default), consolidated or standalone.
symbolNoREQUIRED. The stock symbol, e.g. "RELIANCE" or "TCS".
tickerNoAlias for `symbol`.
periodsNoLatest N periods per section (max 40). Default: all periods when a section is named, 5 per section when it is not.
sectionNoOne of: quarterly, profit_loss, balance_sheet, cash_flow, ratios. `quarterly` is the quarterly P&L; the other four are annual. Omit for all sections.
quartersNoAlias for `periods`.
identifierNoAlias for `symbol`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / as_of
      Added value: +{
      +  "description": "History: only figures public by this date, YYYY-MM-DD.",
      +  "type": "string"
      +}
    • addedInput schema / properties / basis
      Added value: +{
      +  "description": "History: preferred (default), consolidated or standalone.",
      +  "type": "string"
      +}
    • addedInput schema / properties / from
      Added value: +{
      +  "description": "History: earliest period end, YYYY-MM-DD.",
      +  "type": "string"
      +}
    • addedInput schema / properties / to
      Added value: +{
      +  "description": "History: latest period end, YYYY-MM-DD (`meta.next_to` for the next page).",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: pagination via meta.next_to, a 60-period cap per call, sparse coverage before FY2015, and the caveat that as_of values may include later restatements. However, the two modes are described in densely interleaved prose, making the actual call sequence harder to extract than it should be.

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?

Every sentence carries information, but the definition is a dense wall of backticked tokens that mixes schema restatement, mode switching, and pagination in one block. Front-loading the primary default is good, yet the LONG HISTORY passage would read far better as separated lines, and some schema detail (periods max 40) is repeated.

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?

Covers everything an agent needs: allowed sections, default and override behavior, long-history mode with from/to/as_of/basis, pagination, point-in-time semantics, per-section response shape, and the asset-class exclusion. Given no output schema, describing the returned keys (periods, data, pct_changes, row_order, availability) is exactly the right compensation.

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 the baseline is 3; the description earns above that by explaining default behavior (periods defaults differ depending on whether section is set), the ~13-quarter quarterly default, and the eps_basis values as_reported/restated/null. It also supplies a concrete example call showing how symbol, section and periods combine.

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 ("Get financial statements for one company") and enumerates the exact sections available, so an agent knows precisely what data it returns. It also names the sibling get_batch_financials as the alternative for multi-company comparison.

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 rules: one symbol per call, use get_batch_financials to compare companies, and excludes ETFs, index funds and bonds. It also distinguishes the two operating modes (default latest-periods view vs. long-history table) and tells the agent how to page with meta.next_to.

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.