Clarifo

detect_inflection_points

Read-onlyIdempotent

Find where a US company's biggest inflections or turning points occurred in its revenue, profit or margin history. Flags periods whose growth change has an absolute z-score above z_threshold against the company's own volatility (deterministic, from SEC filings).

Args: company: Name, ticker or CIK (US only). metrics: "revenue", "ebit", "ebitda", "net_income" (YoY % change) and "operating_margin", "ebitda_margin", "net_margin" (pp change). Default ["revenue", "ebit", "operating_margin"]. frequency: "annual" (default, 10-K) or "quarterly" (same quarter vs. prior year, 10-Q). z_threshold: Default 2.0; lower catches more, higher only major breaks. top_k: Inflections per metric (1-25, default 5). min_history: Growth points required per metric (default 5); shorter metrics are skipped and noted in quality_notes. market: "us" (only supported value).

Returns series, inflections sorted by absolute z-score (metric, year, quarter, value, prior_value, growth, z_score, direction, severity), narrative_queries (ready queries for search_filing_content) and quality_notes. Annual mode adds sources[] / source_policy: cite with citation_markdown, never the raw page_id. Quarterly points carry no per-quarter filing link.

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": "detect_inflection_points"
  }
}

Input Schema

Name	Required	Default
`top_k`	No
`market`	No	us
`company`	Yes
`metrics`	No
`frequency`	No	annual
`min_history`	No
`z_threshold`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the detection mechanism (z-score of growth change vs. the company's own volatility), the data source (SEC filings, deterministic), skip behavior with min_history and where it is reported (quality_notes), and a citation policy — use citation_markdown, never raw page_id. It also flags a real limitation: quarterly points carry no per-quarter filing link.

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?

The structure is front-loaded: purpose first, then Args, then Returns, with zero filler sentences. The Returns paragraph partly duplicates what the output schema already declares, which is the only mild redundancy; the citation-markdown instruction in it is genuinely non-derivable and earns its place.

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 7-parameter analytical tool with no schema descriptions, the definition covers inputs, methodology, defaults, edge-case skipping, and downstream usage. An output schema exists, so the return-field listing is supplementary rather than required, and the citation caveat closes the remaining practical gap.

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 description coverage is 0%, so the description must carry the full burden, and it does: every parameter is explained with accepted values and units — metrics enumerates all six allowed names and clarifies YoY % change vs. pp change with a default list, frequency maps to 10-K/10-Q with the exact comparison basis, top_k range (1-25), z_threshold default and direction of effect, min_history default and skip semantics, market constrained to 'us'.

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 opening sentence gives a specific verb and resource — finding the biggest inflections/turning points in a US company's revenue, profit or margin history — and names the method (absolute z-score against the company's own volatility, deterministic from SEC filings). An agent can immediately tell this is an anomaly/turning-point analysis tool rather than a plain financials fetch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the analytic context clear and adds tuning advice ('lower catches more, higher only major breaks'; min_history causes metrics to be skipped), plus a downstream hand-off note that narrative_queries feed search_filing_content. However, it never says when to prefer this over siblings such as get_company_financials or forecast_financials, and gives no explicit when-not conditions, so selection guidance is implied rather than stated.

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.