Skip to main content
Glama

Evolc Signals

Search company signals

search_signals
Read-only

Find companies in Europe and the Americas (US, CA, BR, MX) with fresh buying signals: started hiring in a function (e.g. first SDRs), hiring spikes, leadership roles, funding, acquisitions, product launches, expansions, partnerships, milestones, layoffs, revenue jumps, turning profitable, director changes and news. Data comes from company careers pages, ATS job boards, news feeds and public business registers, deepest in Slovakia, Czechia, Poland, Hungary, Austria and Germany. Filters combine with AND; values inside one filter with OR. Returns companies ranked by signal strength with the evidence (title, link, date) for each signal. Company facts only, no people.

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": "search_signals"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoCompany name, website or one-liner contains this text.
daysNoLook-back window in days.
subsNoSub-roles within the chosen families, e.g. sales → sdr_bdr. By family: engineering: backend, frontend, fullstack, mobile, devops_sre, qa, embedded, security, architect, engineering_management; data: data_engineering, data_science, ml_ai, analytics_bi; product: product_management, product_owner, project_management; design: product_design, ux_research, graphic_brand; robotics: robot_programming, plc_controls, mechatronics, robotics_software; manufacturing: cnc_machining, production, maintenance, quality, process_engineering, mechanical_design, welding_fabrication; sales: account_executive, sdr_bdr, sales_management, partnerships, presales_solutions; marketing: growth, content, performance, product_marketing, brand_pr, marketing_management; customer: customer_success, support, account_management, implementation; operations: operations, supply_chain_logistics, office_admin, business_ops; finance: accounting, fp_and_a, controlling; people: recruiting, hr, people_ops; legal: legal, compliance; executive: c_level, general_management; other: .
kindsNoSignal kinds that qualify a company (default: all). hiring = new roles in the window; first_in_function = first role in that function since we began tracking the company (at least 14 days earlier; job history starts 2026-10-16); hiring_spike = 3+ new roles in one function; leadership_role_open = head/director/VP/C-level role opened; revenue_jump and profitability_flip come from registry filings; funding, acquisition, launch, expansion, partnership, milestone and layoffs are moves read from the news (see search_moves); contract_won = signed a public-sector contract as supplier (SK/CZ registers, ≥ €10k); content_push = started or restarted publishing (≥ 3 blog/news posts in 30 days after a quiet period).
limitNoCompanies to return.
sinceNoOnly signals newer than this ISO date or timestamp, e.g. 2026-10-01.
offsetNoSkip this many companies (use `next` from the previous answer).
familiesNoHiring for these job functions. With only event kinds (e.g. funding) the company must also have an open role in one of these functions.
countriesNoISO-2 country codes of the company (SK Slovakia, CZ Czechia, PL Poland, HU Hungary, AT Austria, SI Slovenia, DE Germany, CH Switzerland, HR Croatia, RO Romania, GB United Kingdom, IE Ireland, FR France, BE Belgium, NL Netherlands, LU Luxembourg, ES Spain, PT Portugal, IT Italy, MT Malta, GR Greece, CY Cyprus, DK Denmark, SE Sweden, NO Norway, FI Finland, IS Iceland, EE Estonia, LV Latvia, LT Lithuania, BG Bulgaria, RS Serbia, BA Bosnia and Herzegovina, ME Montenegro, MK North Macedonia, AL Albania, UA Ukraine, MD Moldova, LI Liechtenstein, MC Monaco, AD Andorra, SM San Marino, US United States, CA Canada, BR Brazil, MX Mexico).
industriesNoIndustry keys of the company.
exclude_volumeNoLeave out volume hirers (staffing agencies, branch and field-sales networks, brokers, fundraisers). Set false to include them; they carry volume_hiring: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly and openWorld=false; the description adds substantive behavior beyond that — data provenance (careers pages, ATS boards, news feeds, public registers), depth-of-coverage geography, ranking by signal strength, and returned evidence fields (title, link, date). It also discloses deliberate exclusions (no people data, volume hirers excluded by default and flagged volume_hiring), which is exactly the context an agent needs to interpret results.

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?

One dense paragraph that front-loads the capability, then sources, then coverage, then the AND/OR filter rule and return shape. Every sentence carries information an agent needs; there is no filler or repetition of the title.

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 11-parameter discovery tool with no output schema, the description compensates by describing both the filter algebra and the return payload (ranked companies plus per-signal evidence). Combined with the enum-documented schema, an agent has everything needed to call it correctly and interpret the response.

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?

With 100% schema coverage the baseline is 3, and the description deliberately goes further by defining cross-parameter semantics — AND across filters, OR within one filter — and the rule that event kinds require a matching family filter. That is logic the schema alone cannot express and it directly prevents malformed first calls.

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 verb and resource (find companies with buying signals), names the covered geography and the concrete signal types, and explicitly scopes the tool to 'Company facts only, no people' — which alone separates it from people-oriented siblings. It also cross-references search_moves for the underlying event data, so an agent can place it relative to siblings without opening schemas.

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?

Gives real operating guidance: filters combine with AND while values within one filter OR, event-only kinds require an accompanying open role family, and the `next` cursor from a prior answer should drive offset. It points to search_moves for move semantics. What is missing is an explicit statement of when NOT to use it (e.g. single-company lookup vs get_company), so it stops short of full alternative routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources