Skip to main content
Glama

Top Companies

top_companies
Read-onlyIdempotent

"Who's hiring the most [role]" / "top employers for [job]" / "biggest hirers of [skill]", companies posting the most jobs matching a query/location filter. Use for "who's hiring" analysis, competitive talent landscape.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "what": "frontend developer",
      "country": "us"
    },
    "name": "top_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
whatNo
whereNo
countryYes

Output Schema

NameRequiredDescriptionDefault
leaderboardNoTop companies by job count

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "country": "us",
      +    "what": "frontend developer"
      +  },
      +  {
      +    "country": "de",
      +    "what": "software engineer",
      +    "where": "Berlin"
      +  }
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "leaderboard": {
      +      "description": "Top companies by job count",
      +      "items": {
      +        "properties": {
      +          "count": {
      +            "description": "Number of jobs posted",
      +            "type": "number"
      +          },
      +          "display_name": {
      +            "description": "Company name",
      +            "type": "string"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds the meaningful behavioral fact that results are aggregated per company by posting count, but says nothing about how many companies are returned, ranking window/time period, or coverage limits of the open-world data source.

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?

Two tight sentences with no filler, but the sentence leads with three quoted user phrasings rather than the functional statement, pushing the actual definition of the result set to the back half. The quoted phrasings do aid intent matching, so the slight front-loading cost is tolerable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value description is not required, and annotations cover safety. Still, for a 3-parameter open-world aggregation tool with zero schema coverage, the definition leaves open the default ranking window, result caps, and country-code conventions that an agent would need to call it well.

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 0%, so the description must carry parameter meaning: it maps [role]/[job]/[skill] to the keyword filter and 'location filter' to the geographic params, which is partial compensation. It never distinguishes `what` from `where` versus `country`, nor explains the country code format or what happens when the optional `what` is omitted.

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?

The clause "companies posting the most jobs matching a query/location filter" states the resource (companies) and the aggregation (ranked by posting count), which is more than the name alone conveys. The verb is implied rather than explicit, and no sibling (e.g. adzuna_search) is named for contrast, so an agent must infer that this aggregates by employer rather than listing individual postings.

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?

The quoted trigger phrasings ("who's hiring the most [role]", "top employers for [job]", "biggest hirers of [skill]") plus the stated analysis contexts ("who's hiring", "competitive talent landscape") give clear when-to-use signals. There is no when-not guidance and no named alternative for the case where the user wants the actual job listings rather than employer rankings.

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.