Genexxis paid agent tools (x402)

dealdocs_financials

Financial statements to normalised JSON per period (IFRS, US GAAP, PCG, CGNC...), audit opinion, plus ratios computed in code (margins, ROE, net debt/EBITDA, interest cover, liquidity, DSO/DIO/DPO, FCF, cash conversion), balance checks and flags. Up to 25 PDF pages / 2.5 MB / 100k characters (larger: /financials/pro). Long jobs return a free poll URL. Documents are not stored. Price: $0.99 USDC per call, paid with x402 on Base.

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": "dealdocs_financials"
  }
}

Input Schema

Name	Required	Description
`url`	No	https link to the document (PDF, HTML or plain text)
`text`	No	Document text (min 200 characters). Send exactly one of text, url, pdf_base64.
`docType`	No	Optional hint: auto, term_sheet, safe_or_convertible, shareholders_agreement, loi_or_offer, spa_or_apa, nda
`language`	No	Optional output language: auto, en, fr, es, de, it, pt, nl, ar; default auto (language of the document)
`pdf_base64`	No	The PDF file, base64-encoded
`perspective`	No	Optional, red flags only: whose side to review for (neutral, investor, founder, company, buyer, seller, lender, borrower, minority_shareholder, majority_shareholder); default neutral

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 30, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the load and does well: it discloses the size limits that trigger rejection, the async polling behavior for long jobs ('free poll URL'), the data-retention stance ('Documents are not stored'), and the cost model ('$0.99 USDC per call, paid with x402 on Base'). It does not cover failure modes, partial-extraction behavior, or what a paid-but-failed call costs.

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?

Everything is front-loaded in two dense sentences and each clause carries information (capabilities, limits, polling, retention, price). The chain of ratio abbreviations is compressed readable shorthand rather than padding, though the run-on construction makes it slightly harder to scan than a structured list.

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?

There is no output schema, so the description must characterize the return value, and it does so by naming the output form (normalised JSON per period) and the computed categories (margins, ROE, net debt/EBITDA, DSO/DIO/DPO, FCF, cash conversion, balance checks and flags). For a six-parameter extraction tool that is nearly sufficient, with only the concrete response shape and error semantics missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and every parameter is documented, including the 'send exactly one of text, url, pdf_base64' constraint, so baseline 3 applies. The description adds little per-parameter meaning and actually introduces mild friction by advertising IFRS/US GAAP/PCG/CGNC standards while the docType enum enumerates legal-document types, and it never mentions the perspective parameter that exists 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 transformation (financial statements → normalised JSON per period), names the accounting standards handled, and enumerates the derived outputs (ratios, audit opinion, balance checks, flags). An agent can distinguish it from dealdocs_financials_pro purely on the size cutoff and from dealdocs_redflags by the financial-statement focus.

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?

Explicitly routes oversized inputs to the sibling: 'Up to 25 PDF pages / 2.5 MB / 100k characters (larger: /financials/pro)', which is a clear alternative-plus-condition. It stops short of distinguishing itself from non-sibling options like edgar_financials or stating when extraction is inappropriate, so it is not a full when/when-not treatment.

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

All Genexxis paid agent tools (x402) 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?