Skip to main content
Glama

ares

by dev.cz-agents
OverviewDiscussionsAdmin

search_companies

Read-only

Search ARES by company name, city, street, PSČ, or NACE code. Combines all filters with AND. Useful when user knows name but not IČO, looking for companies in a building, or all businesses in a sector.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pscNoFilter by postal code (PSČ), 5-digit number.
cityNoFilter by city (nazev obce), e.g. "Praha".
naceNoFilter by CZ-NACE activity codes, 2-6 digits. E.g., ["62"] for IT.
pocetNoMax results (1-100, default 10).
queryNoPartial or full company name (obchodní jméno).
startNoPagination offset (default 0).
streetNoFilter by street name (nazev ulice), e.g. "Radlická".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. Changed5 schema fields changed
    • changedInput schema / properties / city / description
      Previous value: -"Filter by city (nazev obce)."New value: +"Filter by city (nazev obce), e.g. \"Praha\"."
    • addedInput schema / properties / nace
      Added value: +{
+  "description": "Filter by CZ-NACE activity codes, 2-6 digits. E.g., [\"62\"] for IT.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / pocet / description
      Previous value: -"Max results to return (1-100, default 10)."New value: +"Max results (1-100, default 10)."
    • changedInput schema / properties / psc / description
      Previous value: -"Filter by postal code (PSČ)."New value: +"Filter by postal code (PSČ), 5-digit number."
    • addedInput schema / properties / street
      Added value: +{
+  "description": "Filter by street name (nazev ulice), e.g. \"Radlická\".",
+  "type": "string"
+}
  8. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds the non-obvious behavioral detail that 'Combines all filters with AND', which materially affects query construction and result interpretation. It does not disclose return format or pagination trends, but those are partially described in the schema.

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?

Two sentences, both dense with meaning: the first defines the search scope, the second explains filter combination and typical use cases. No redundancy or filler.

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?

For a read-only search tool with 7 optional parameters and no output schema, the description provides purpose, usage scenarios, and filter logic. It could mention pagination (start, pocet) or result limits, but those are already in the schema. The description is sufficient for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are individually documented. The description adds semantic value by clarifying that all filters are combined with AND, which is a cross-parameter behavior not obvious from individual descriptions. It also maps the free-text query and structured filters to real-world search intentions.

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 clearly states 'Search ARES by company name, city, street, PSČ, or NACE code' — a specific verb, resource, and supported filters. It distinguishes from siblings like lookup_by_ico (by IČO), search_by_address, and search_by_nace by covering a multi-filter search scenario.

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 description provides concrete use cases: 'when user knows name but not IČO, looking for companies in a building, or all businesses in a sector.' It implies alternatives (e.g., lookup_by_ico for IČO) without naming them explicitly, but the context is clear enough for an agent to make a good choice.

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

All ares toolsInspect
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