Clarifo

discover_companies

Read-onlyIdempotent

Find companies by qualitative business profile (semantic search over Clarifo's company profiles for US and Nordic FI/SE/DK companies). Use for "which companies do X" / "companies like Y" questions where the criterion is the business description. For metric-based ranking use screen_companies; for filing passages use search_filing_content. No figures are returned; fetch them with get_company_financials or screen_companies on the returned names.

Args: query: Natural-language description, e.g. "US SaaS companies serving banks", "Companies similar to GE Vernova". limit: Companies to return (default 10, max 50). locale: Profile locale, "en" (default) or "fi". country: ISO-2 code ("FI", "SE", "DK", "US", ...). market: "nordic" or "us"; ignored when country is set. tag_filters: Per-section tag intersections; sections products_services, customers, geography, risks, accounting. E.g. {"geography": ["United States"]}. hybrid_alpha: 0.0 = keyword (BM25), 1.0 = vector (default). Below 1.0 adds keyword scoring, which is rate-limited. size_weight: 0.0-1.0 tie-break lifting larger companies (default 0.3); 0.0 for pure semantic ranking (niche / small-cap matches).

Returns companies (company_name, ticker, country, industry, profile_snippet, matched_tags, page_id, score, blended_score) and coverage. page_id points to a company profile, not a filing; for quotable filing evidence use search_filing_content.

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": {
      "query": "<query>"
    },
    "name": "discover_companies"
  }
}

Input Schema

Name	Required	Default
`limit`	No
`query`	Yes
`locale`	No	en
`market`	No
`country`	No
`size_weight`	No
`tag_filters`	No
`hybrid_alpha`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Beyond the readOnly/openWorld annotations it discloses non-obvious behavior: no figures are returned, keyword scoring below alpha 1.0 is rate-limited, market is ignored when country is set, and page_id points at a profile rather than a filing. The only missing piece is scale/latency expectations for a semantic search over a whole universe.

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-loaded with purpose and sibling routing before the Args block; sentences are dense and mostly earn their place. The Returns paragraph restates field names already carried by the output schema, which is minor redundancy rather than harm.

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 an eight-parameter semantic search with an output schema, the description covers the universe, scoring knobs, rate-limit caveat, follow-up tools, and the crucial profile-vs-filing distinction. Nothing an agent needs to call it correctly appears to be missing.

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%, yet all eight parameters are explained with defaults, bounds (limit max 50, size_weight 0.0-1.0, hybrid_alpha 0.0/1.0 semantics), concrete examples, and an inter-parameter rule (country overrides market). It also enumerates the tag_filters sections, which the schema cannot express.

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?

Opens with a specific verb+resource ("Find companies by qualitative business profile") and immediately scopes it to semantic search over Clarifo company profiles for US and Nordic FI/SE/DK names. It explicitly contrasts itself with screen_companies (metric ranking) and search_filing_content (filing passages), so an agent can pick it without opening any schema.

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

Usage Guidelines5/5

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

Gives concrete trigger phrasing ("which companies do X" / "companies like Y" where the criterion is the business description) plus explicit exclusions routed to named alternatives for metrics and filing passages. It also states the follow-up path (fetch figures with get_company_financials or screen_companies on the returned names), removing the main wrong-turn.

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.