Classify a free-text business description into top-K NOGA 2025 codes with confidence scores. Uses pre-computed Xenova/paraphrase-multilingual-mpnet-base-v2 embeddings (768d, FR). NACE 2.1 mode falls back to NOGA 2025 in v1 — combine with cross_walk for translation.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | fr | |
| text | Yes | Free-text business description (FR) | |
| top_k | No | ||
| scheme | No | NOGA_2025 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the use of specific pre-computed embeddings (Xenova/paraphrase-multilingual-mpnet-base-v2, 768d, FR) and the fallback behavior of NACE 2.1 mode to NOGA 2025. These are meaningful behavioral details beyond what the schema shows, though it does not describe the output structure or error 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 three sentences with no fluff. It front-loads the core purpose, then provides technical and fallback context in a compact manner. Every sentence adds value without redundancy.
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 tool with no output schema and no annotations, the description covers the essential context: purpose, parameters, language, model detail, and a fallback caveat. It mentions confidence scores as output, which gives a high-level idea, but does not detail the exact return structure. Still, it is sufficiently complete for an agent to invoke the tool correctly in most cases.
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 only 25% (only 'text' has a description). The description compensates by clarifying the semantics of multiple parameters: 'text' as free-text business description, 'top-K' implying top_k, and 'NACE 2.1 mode' explaining the 'scheme' parameter. It also reinforces the 'lang' restriction (FR) via the model mention. This goes beyond the sparse schema descriptions.
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 action: 'Classify a free-text business description into top-K NOGA 2025 codes with confidence scores.' It specifies the verb (classify), resource (free-text business description), and output (codes with confidence), which distinguishes it from sibling lookup tools.
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 provides clear context for when to use the tool (when business descriptions need NOGA classification). It also gives conditional guidance for NACE 2.1 mode, explicitly advising to 'combine with cross_walk for translation,' which is a form of alternative usage direction. However, it does not explicitly exclude other tools or provide a comprehensive when-not-to-use list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
finma_search and kyc_check overlap heavily; both search the FINMA registry by name, and kyc_check essentially does what finma_search does with include_warnings=true. The other tools are distinct, but this pair creates real selection ambiguity.
Names mix verb-first (classify_text), noun-first (finma_search, tariff_lookup), and pure nouns (cross_walk, entity_history). All are lowercase with underscores, so it's readable, but the inconsistent verb placement breaks a predictable pattern.
9 tools is well-scoped for a server covering multiple Swiss data domains (classifications, FINMA, tariffs, statistics). Each tool serves a distinct purpose and earns its place without being overwhelming.
The set covers core workflows: text classification, code mapping, entity search/history, tariff lookup/changelog/search, and statistics. Minor gaps like a direct get-entity-by-UID endpoint or more granular statistics exist, but agents can work around them.
