Clarifo

dd_quickscan

Read-onlyIdempotent

Build a pre-due-diligence evidence pack for one target company from public filings. No LLM runs on Clarifo's side: you reason over the evidence. It does not replace bespoke due diligence. Three branches, run in parallel:

Financial trends: revenue, EBIT, operating margin, operating cash flow and derived cash conversion (OCF / EBIT, %) over years. All series are REPORTED IFRS / US-GAAP figures (trend_basis); do not compare them with adjusted / comparable EBIT without the bridge from the earnings_quality bucket.
Period view (period_financials): freshness compares the trend series with the newest filing on file and appends a filed fiscal year the series lacks (supplemented_periods); fiscal_years (last 3), quarters (last 8 fiscal quarters: revenue, gross / operating margin, operating cash flow, capex, FCF, TTM FCF; derived names each computed value's formula), latest_quarter vs the same quarter a year earlier, and the newest quarter's earnings_bridge and cash_bridge (computed lines vs unexplained_residual). State reporting_period and gaps in every brief.
Valuation (valuation): P/E, EV/EBIT and FCF yield on one share price (price.trading_date) and one earnings_period (TTM through the latest quarter, else the latest fiscal year). Quote both with the numbers. Reported basis only: never present an adjusted multiple (adjusted.shown is false). checks names where the TTM window disagrees with period_financials.
Materiality evidence: recent filing chunks in five buckets (audit / KAM / going concern, governance, risks and covenants, outlook and subsequent events, earnings quality) plus Clarifo's rubric. Apply that rubric and cite each chunk's source_id. For a material item, show its accounting treatment (measurement basis, amount, statement line, note) only as the chunk prints it, with the chunk's citation as the note link.
CSRD disclosure coverage: per-ESRS coverage overall and by E/S/G pillar, with ranked gaps. Measures how much is disclosed, not its quality: not a compliance verdict.

Args: company: Target name or ticker, e.g. "Caterpillar", "CAT". market: "auto" (default), "EU" or "US". Only "US" skips the CSRD branch, so pass it for US companies. language: "en" (default) or "fi". years: Trend window (2-10, default 4). include_csrd / include_materiality: Toggle those branches. recency_years: Retrieval window in fiscal years (default 2; 0 = all). materiality_search_limit: Max chunks (4-60, default 24). document_types: Optional filter, e.g. ["annual_report"].

Returns: {company, market, financial_trends, trend_basis, materiality_evidence {instructions, rubric, chunks[]}, csrd_summary (None when skipped), sources, coverage, audit}. coverage gives each branch's outcome (ok / no_data / failed): report gaps from it. Materiality no_data means the filing text was not retrieved (risks_assessed: false), never that the company has no material risks: say so. coverage.audit_report.found = false means the auditor's report was not in the indexed text: say it must be checked in the filing (check_in), never that the audit is clean. Never annualise an effect a filing states for one quarter. On error: {"error", "company"}.

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": {
      "company": "<company>"
    },
    "name": "dd_quickscan"
  }
}

Input Schema

Name	Required	Default
`years`	No
`market`	No	auto
`company`	Yes
`language`	No	en
`include_csrd`	No
`recency_years`	No
`document_types`	No
`include_materiality`	No
`materiality_search_limit`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare read-only/idempotent/non-destructive, yet the description adds substantial behavior: no LLM runs server-side, branch-level coverage outcomes (ok/no_data/failed), and explicit interpretive rules such as materiality no_data meaning retrieval failure and audit_report.found=false meaning 'check the filing,' never 'clean.' It also flags the error shape and warns against annualising single-quarter effects — far beyond annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite its length it is well front-loaded (purpose sentence, then parallel branches, then Args, then Returns) and each line carries operational meaning for a complex multi-branch tool. Minor redundancy between the Returns section and the existing output schema, but nothing is filler.

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 9-parameter, multi-branch composite tool this is complete: it describes each branch's contents, the args, the return envelope, error shape, and the interpretation caveats an agent needs to report honestly. Even with an output schema present, the semantic warnings about no_data and audit coverage are essential and included.

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

Parameters5/5

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

Schema coverage is 0%, so the description carries the full burden, and it does: every one of the nine args gets meaning, defaults, ranges and examples (e.g. years 2-10 default 4, recency_years 0 = all, materiality_search_limit 4-60, document_types example). This fully compensates for the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Build a pre-due-diligence evidence pack for one target company from public filings,' and scopes it to a single company, which implicitly distinguishes it from portfolio-level siblings like compare_companies. It does not explicitly route away from or toward named sibling tools (e.g. get_company_financials), so it falls short of a 5.

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?

Explains the intended context (pre-due-diligence) and sets an explicit boundary ('does not replace bespoke due diligence'), plus concrete routing guidance for the market arg ('Only US skips the CSRD branch, so pass it for US companies'). It never names an alternative tool to use when this one is unsuitable, which keeps it at 4.

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

All Clarifo 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.