FinancialMD

Proof for a value

proof_get

Read-onlyIdempotent

Return the full proof behind a value: the proof itself (filing accession, form and filing date, XBRL taxonomy, tag and dimensions, source URL, page and anchor), the kind (std for a standardized value, ar for a raw as-reported fact), the value object, the concept it maps to, the company, the filing summary, the raw as-reported facts the standardized value derives from, and the derivation (method, calc_type and the pipeline run). For a ratio (kind "ratio") it also returns the formula and the standardized input values, each with its own proof. Every value object carries proof.id; pass it here when a person asks "where does this number come from" or before quoting a figure in a report. A human page exists at meta.proof_base + proof_id. Metadata call: free on every tier. If a dataset, field, company or analysis you need is missing, call request_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": {
      "proof_id": "p_01JCA4Q7Z3K8M2N5R9T1V6X0Y2"
    },
    "name": "proof_get"
  }
}

Input Schema

Name	Required	Description	Default
`proof_id`	Yes	The proof id from a value object, for example p_01JC....

Output Schema

Name	Required	Description
`data`	No	{ proof, kind (std or ar), value, concept { concept_id, label, statement } or null, company, filing, derived_from (raw facts), derivation { method, calc_type, run } or null }.
`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

A4.3/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the cost and access context: "Metadata call: free on every tier," plus the human-readable page at meta.proof_base + proof_id, and the fact that ratios recursively include input proofs. That is genuine behavioral disclosure beyond the structured fields.

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 first clause is well front-loaded, but the long comma-separated inventory of returned fields (filing accession, form, XBRL taxonomy, tag, dimensions, source URL, page, anchor, derivation method, calc_type, pipeline run) is verbose and largely duplicates what the existing output schema already declares. It remains one readable paragraph, but several clauses do not earn their space.

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?

For a single-parameter, read-only lookup with an output schema and full annotation coverage, nothing an agent needs is missing: it knows how to obtain the id, what the call costs, what the recursive ratio case yields, and where to escalate for missing data. The complexity-to-description ratio is appropriate.

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% with a single required proof_id, so the schema already does most of the work. The description still adds meaning by explaining provenance — the id comes from proof.id on any value object — which tells an agent where to source the argument rather than guessing.

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 description opens with a specific verb and resource ("Return the full proof behind a value") and immediately enumerates the payload: proof contents, kind (std/ar), value object, concept, company, filing summary, source facts, and derivation. The std/ar and ratio distinctions give an agent a precise picture of what comes back, which is well beyond a restatement of the title.

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?

It states the triggering condition concretely: pass proof.id here "when a person asks 'where does this number come from' or before quoting a figure in a report," and explains how the id is obtained ("Every value object carries proof.id"). It also routes a different need (missing dataset/field/company) to request_data, though it gives no explicit when-not-to-use relative to a validation sibling such as verify_value.

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?