FinancialMD

Tell FinancialMD what data you need

request_data

Tell FinancialMD about data you needed and did not find: a dataset or field we lack, a company we do not cover, an analysis you had to do by hand, or an answer that looked wrong. Use it when no other tool serves what you need. Send kind and one or two sentences in want; why, company and the tool you were using help. Free, takes seconds and needs no key or account. Similar requests are merged and count as votes; they are reviewed weekly and the most asked-for data is built first. The answer has a request_id to follow with request_status. Do not include personal data.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "why": "Comparing reported EPS with expectations",
      "kind": "dataset",
      "want": "Consensus EPS estimates for the next two quarters",
      "company": "AAPL",
      "endpoint_or_tool": "company_kpis"
    },
    "name": "request_data"
  }
}

Input Schema

Name	Required	Description
`why`	No	Optional: the task it blocks.
`kind`	Yes	dataset: a whole dataset we lack; field: a line item or attribute; analysis: a computation; coverage: a company or market we do not cover; bug: a wrong or broken answer; other.
`want`	Yes	What you needed and did not find, in one or two sentences.
`company`	No	Optional: the company it concerns (ticker, CIK or name).
`endpoint_or_tool`	No	Optional: the tool or route you were using, for example "ratios".

Output Schema

Name	Required	Description
`data`	No	{ request_id, item_id, status, requests, requesters, status_url, served_by, message, next }: the stored request, the demand item it joined and what happens to it.
`meta`	No	Request metadata: request_id, as_of, company resolution, coverage, pipeline_version, licence, terms, proof_base.
`error`	No	Present only on isError results: the API error code and message plus remedy hints.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing what happens to a submission: similar requests are merged and count as votes, review happens weekly, the most asked-for data is built first, and it is free with no key or account. It also states the return contains a request_id for follow-up and adds a privacy constraint ('Do not include personal data'), which is exactly the kind of behavioral context annotations cannot carry.

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-loads the purpose and packs a lot of high-value detail into a short paragraph; every sentence carries routing, behavior, or privacy information. The phrasing is slightly run-on in places ('Send kind and one or two sentences in want; why, company and the tool you were using help'), which costs a point on structure but not on content.

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?

An output schema exists, so return values need not be explained, yet the description still flags the request_id handoff to request_status. Combined with dedupe/voting behavior, review cadence, access cost, and the personal-data warning, an agent has everything needed to decide to call it and how to fill it in correctly.

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, but the description adds meaning beyond it by indicating which fields are required (kind and a one-or-two-sentence want) versus merely helpful context (why, company, the tool in use). The only miss is that it does not enumerate the kind enum values, since those already live in the schema.

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 — tell FinancialMD about data you needed and did not find — then enumerates concrete cases (missing dataset/field, uncovered company, manual analysis, wrong answer). The final scope line 'Use it when no other tool serves what you need' makes it unmistakable versus the sibling lookup/analytics tools.

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 a clear selection rule ('when no other tool serves what you need') that functions as a catch-all fallback, which is the right routing cue for a request tool in a large catalog. It also names the follow-up path (request_status with the returned request_id), though it does not spell out when to prefer filing_search or coverage checks first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FinancialMD tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?