Evolc Signals

Find customers for a company

find_customers_for

Idempotent

Give a company website and get the companies in Europe and the Americas most likely to buy from it that changed recently (hiring in the team that buys, a new leader, funding, better numbers), each with the fit reason, an opening line and the evidence links, plus a read-only link to the live list that can be forwarded to that company. Evolc reads the website first; the first call for a new site answers "analysing" (free) and the same call about two minutes later returns the list. The analysis is kept in your account and reused.

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": {
      "domain": "<domain>"
    },
    "name": "find_customers_for"
  }
}

Input Schema

Name	Required	Description
`goal`	No	Optional: what kind of customers to look for, in a sentence.
`limit`	No	Accounts to return (default and cap depend on the plan: 5 on work, 25 on paid).
`domain`	Yes	The company website, e.g. "acme.com".
`countries`	No	Up to 12 ISO-2 codes to rank first (one code also filters the list).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, openWorldHint=true), the description discloses the non-obvious asynchronous behaviour: a new domain triggers a free 'analysing' response, and the analysis is cached in the account and reused, which explains the idempotency hint in operational terms. It also states that the first call is free and that the produced link is read-only and forwardable.

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?

Three sentences, front-loaded with the core action and result, followed by the operational caveat about the 'analysing' state. The long opening sentence carries real payload (returned fields, shareable link) rather than filler; nothing is redundant with the schema.

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?

With no output schema, the description compensates by enumerating the returned fields (fit reasons, opening lines, evidence links, live-list link). The async/caching behaviour is covered. Minor gaps remain around error states (e.g. unreachable domain) and how the plan-based limit interacts with retries, but nothing essential to a correct first call is 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 description coverage is 100%, so the baseline is 3. The description reinforces 'domain' as the company website and hints at geography ('Europe and the Americas'), but it adds nothing about the 'goal', 'limit' (plan-dependent cap), or the 'countries' ranking-vs-filtering distinction that the schema already documents.

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 names a specific input (a company website/domain) and a specific output (European/American companies likely to buy, with fit reason, opening line, evidence links and a shareable live-list link). That is far more concrete than the sibling names search_signals or search_moves imply, and it makes clear this is a seed-company-driven prospecting tool rather than a signal or tender search.

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 gives a clear entry condition ("Give a company website and get...") and explains the two-step invocation pattern: the first call for a new site returns 'analysing' for free, and repeating the same call in ~2 minutes yields the list. It does not explicitly contrast itself with siblings such as search_signals or check_accounts, so there is no when-not-to-use guidance.

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

All Evolc Signals 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?