Sourced, dated records of family offices in Switzerland, Liechtenstein, Austria, Germany and Dubai.
Scored across 2 tools
get_record retrieves a single firm by ID, while search_registry performs a query-based search. Their purposes are clearly distinct with no overlap, making selection unambiguous.
Both tools follow a consistent verb_noun snake_case pattern (get_record, search_registry). The slight difference in noun (record vs registry) reflects distinct entities, not a naming inconsistency.
Only two tools are provided for a registry server, which is on the thin side. While search and get may cover basic lookup, a count of 2 falls into the borderline range per the rubric (1-2 tools feels thin).
The core operations of searching and retrieving a record are covered, including subscription-aware detail levels. Minor gaps exist, such as no explicit pagination tool or bulk retrieval, but agents can likely work around these using search parameters.
One firm by its registry id. Without a subscription key this returns the open fields and says how many named roles the full record holds; with one it returns the named roles, the contact channels, the full source list and the verification note.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Registry id, as returned by search_registry. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does substantial work: it discloses that the response payload varies by authentication (open fields plus a role count without a subscription key, full roles/contacts/sources/verification note with one). It omits failure behavior for an unknown id and any permission/rate context.
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?
A single sentence, front-loaded with the subject ('One firm by its registry id') followed by the conditional payload split. Every clause conveys new information; nothing is padded or repeated from the schema.
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?
With no output schema, the description correctly compensates by enumerating the returned fields under both auth states, which is exactly what an agent needs to reason about results. The remaining gap is error/not-found behavior for an invalid id.
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?
There is a single parameter with 100% schema description coverage, so the schema already explains that id is the registry id from search_registry. The description adds no syntax, format, or validation detail beyond that, making the 3 baseline appropriate.
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?
States a specific verb and resource: fetch exactly one firm identified by its registry id. The singular 'one firm' implicitly contrasts with the sibling search_registry, though it never names the sibling or explicitly says 'use this instead of search when you already have an id'.
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?
Usage is implied rather than stated: the schema note 'as returned by search_registry' and the singular resource suggest the search-then-fetch flow, but the description gives no explicit when-to-use, when-not-to-use, or alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search verified family offices and related firms in Switzerland, Liechtenstein, Austria and Germany, and single-family offices in Dubai (free, with no named people). Returns one page of open records — the same fields the public site publishes. Named people, contact channels, source lists and verification notes need a subscription. Read the skill resource before answering from these results.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Free text. Without a key it looks in the open fields (name, city, register id, legal form, focus tags); with one, in the people and the purpose clauses too. For a place, filter by canton or country. | |
| page | No | ||
| size | No | Results per page, capped at 25 without a subscription key. | |
| type | No | ||
| alloc | No | Subscription only: list firms by how they invest. Without a key the search refuses this filter; get_record gives any one firm's call free. | |
| canton | No | Swiss canton code, e.g. ZH, ZG, GE. | |
| country | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does it well: it discloses that results are free and de-identified ('no named people'), that named people/contact channels/source lists/verification notes are subscription-gated, and that only one page of open records is returned. It stops short of describing rate limits or pagination mechanics beyond 'one page'.
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?
Four sentences, front-loaded with the core capability and scope before the gating and the skill-resource reminder. Each sentence earns its place, though the subscription detail is slightly repetitive with the schema's own gating notes.
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?
With no output schema and no annotations, the description covers the essentials: geographic scope, free vs paid content, return granularity, and a pointer to the skill resource. It is nearly complete, lacking only explicit alternative-tool routing and pagination behavior.
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?
Schema description coverage is 57%, so the schema already documents several parameters in detail, including `q` and `size`. The description adds scope context (geography, free tier, public-site fields) but no per-parameter syntax or semantics beyond what the schema provides, so a baseline 3 is appropriate.
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 states a specific verb (search) and resource (verified family offices and related firms), and pins the geographic scope precisely (CH, LI, AT, DE, and SFOs in Dubai). It is clear what the tool returns, but the main description never names or distinguishes itself from its sibling get_record — that routing only appears buried in the `alloc` schema note.
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?
Usage is implied through the free-vs-subscription framing and the instruction to 'read the skill resource before answering,' but there is no explicit when-to-use guidance or comparison against get_record inside the description itself. An agent must infer that single-firm lookups belong to get_record rather than this list tool.
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_recordsearch_registryFamily Office Knowledge Graph: read-only MCP door over the public record. Agentic KG Holdings.
Verified European PE ownership: who owns a company, GP portfolios, exits by year. Hand-checked.
UBO, sanctions & ownership graph. 23 tools, 130.7M entities, 31 registries.
Verified company profiles, financials, ownership, registry records and business contacts.
Add one secure layer between your agents and this server.
