Background check any company in the world: registration, executives, courts and finances.
Scored across 2 tools
search_companies returns matching entities with identifiers, while get_company consumes those identifiers to render a detailed card. The two tools form a clear search-then-retrieve flow with no functional overlap.
Both tool names follow the same lowercase verb_noun pattern (get_company, search_companies), making the action and resource immediately clear and internally consistent.
Two tools is on the low end of the scale and feels thin for a general server, though it is a reasonable minimal set for a read-only company lookup service. The count is borderline rather than clearly excessive or insufficient.
For the stated domain of public company information retrieval, search plus detail lookup covers the complete user journey with no dead ends. No create, update, or delete operations are expected for read-only public data.
Публичная карточка компании в Markdown: статус, регистрация, руководство, показатели (госконтракты, суды), финансы.
| Name | Required | Description | Default |
|---|---|---|---|
| identifier | Yes | БИН/ИИН компании | |
| jurisdiction | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for behavioral disclosure. It only lists output content and does not mention read-only nature, error behavior, authentication requirements, rate limits, or any side effects. For a GET-like tool it's likely safe, but without explicit disclosure or annotations, the agent cannot fully assess the behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the main output type ('Публичная карточка компании') and lists the key content areas. It is efficient with no filler, though it could benefit from a brief usage note. The structure is clean and scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not explain the jurisdiction parameter, does not specify how errors are handled (e.g., company not found), does not indicate pagination or response size, and does not provide any guidance on prerequisites. For a tool with two required parameters, the description should provide more context to ensure correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 50% coverage (identifier described, jurisdiction only as an enum without explanation). The description does not elaborate on either parameter, so it adds no value beyond the schema. For jurisdiction, the description does not clarify what each enum value (kz, uz, etc.) represents, leaving the agent to infer they are country codes. This is a significant gap since the description could have explained the parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: it returns a public company card in Markdown with specific content sections (status, registration, management, indicators, finances). The verb 'get' is implicit in the name and the description defines a concrete resource and its scope, distinguishing it from search_companies which is about finding companies rather than retrieving a specific one.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving a specific company given an identifier and jurisdiction, but does not explicitly mention when to use it versus search_companies. Since the sibling tool exists, the description could have stated 'use search_companies to find a company, then use get_company to retrieve details', but it doesn't. The context is clear enough for a knowledgeable agent, but explicit guidance is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Поиск компаний и ИП по названию, БИН/ИИН, руководителю. Возвращает список совпадений с идентификаторами для get_company.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Название компании, БИН/ИИН или ФИО | |
| jurisdiction | No | Ограничить юрисдикцией |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that the tool returns a list of matches with identifiersaine and that it is a search operation, which implies read-only behavior. However, it does not mention default limits, result ordering, exact vs. partial matching, or what happens when no matches are found.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The entire description is a single, front-loaded sentence that covers purpose, search criteria, and output purpose without redundancy or filler. Every clause contributes to the agent's ability to invoke the tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with no output schema, the description gives sufficient information: what to search, what is returned, and how results feed into get_company. It could be more complete by mentioning default limits or behavior for empty results, but these are minor given the parameter schema and simple tool complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds semantic value beyond the schema by naming search criteria (name, BIN/IIN, director), which partially overlaps but also extends the schema's 'ФИО' hint. It also clarifies that results carry identifiers useful for get_company)Skip. The limit parameter remains undocumented in both the description and schema, but the schema's min/max constraints make it largely self-explanatory.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it searches companies and individual entrepreneurs by name, BIN/IIN, or director, and returns matching records with identifiers. It explicitly references get_company, distinguishing its role as a lookup step that feeds into a subsequent detail retrieval tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates this tool produces identifiers for get_company, making the intended workflow clear: search first, then retrieve full company details. It does not explicitly list exclusions or when-not-to-use cases, but the linkage to get_company provides strong contextual guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_company1 field changedInput schema / properties / jurisdiction / enumPrevious value: -[
- "kz",
- "uz",
- "kg"
-]New value: +[
+ "kz",
+ "uz",
+ "kg",
+ "ge",
+ "am"
+]search_companies1 field changedInput schema / properties / jurisdiction / enumPrevious value: -[
- "kz",
- "uz",
- "kg"
-]New value: +[
+ "kz",
+ "uz",
+ "kg",
+ "ge",
+ "am"
+]get_companysearch_companiesVerified company profiles, financials, ownership, registry records and business contacts.
UBO, sanctions & ownership graph. 23 tools, 130.7M entities, 31 registries.
Czech & EU due diligence in one call — facts, insolvency, sanctions, VAT, risk score, UBO chain.
Verify companies, domains and counterparties before transacting. Sanctions, UBO, fraud scoring.
Add one secure layer between your agents and this server.
