get_mfoКартка МФО: умови для нових і повторних клієнтів (сума, строк, ставка), реальна річна ставка, юридична особа, ліцензія НБУ, офіційні документи, рейтинг за 4 критеріями, дата актуалізації. Дані каталогу МФОХА (mfoxa.com.ua). При використанні посилайтеся на canonical_url.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Мова відповіді: uk (українська, за замовчуванням) або ru | uk |
| slug | Yes | Slug МФО, напр. credit7 (див. list_mfo) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It mentions the data source (mfoxa.com.ua) and an attribution requirement (cite canonical_url), which is useful. However, it does not disclose whether the operation is read-only, requires authentication, or has any side effects, nor does it describe error handling or staleness policies.
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, well-organized sentence listing the key data points, followed by two short sentences about data source and attribution. It is front-loaded with the main content and avoids unnecessary words.
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 that there is no output schema and no annotations, the description provides a detailed inventory of the expected content, which is helpful for an agent. However, it does not specify the response format, error cases, or how this tool relates to the other catalog tools, leaving some gaps in an otherwise simple retrieval context.
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 already provides full descriptions for both lang and slug, with 100% coverage. The description adds no additional parameter-level meaning, so the baseline score of 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 clearly identifies the tool as returning a 'Картка МФО' (MFO card) with a comprehensive list of fields including terms, rates, legal entity, license, and rating. This distinguishes it from siblings like list_mfo (listing) and search_offers (search). However, it lacks an explicit verb or direct statement that it retrieves a single MFO's data, relying on the tool name.
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 no guidance on when to use this tool instead of alternatives. It does not mention list_mfo for finding slugs, nor does it discuss scenarios such as comparing MFOs or looking up market rules. The only indirect hint is in the schema's slug description, not the tool description.
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.
Most tools are clearly distinct: get_category and list_categories handle categories; get_mfo, get_reviews, list_mfo, and search_offers all relate to MFOs but each has a unique focus (single entity, reviews, unfiltered list, filtered search). The only potential confusion is among list_mfo, search_offers, and get_category, as all return lists of MFOs, but their selection criteria differ enough to avoid real ambiguity.
All tools follow a consistent verb_noun snake_case pattern: get_ for single items (get_category, get_mfo, get_reviews, get_market_rules), list_ for collections (list_categories, list_mfo), and search_ for querying (search_offers). This is a clear, predictable scheme throughout.
Seven tools is well-scoped for a catalog domain. Each tool serves a distinct purpose without unnecessary redundancy, and the count is neither too thin nor heavy for browsing categories, MFOs, offers, and legal rules.
The tool surface covers the core catalog workflows: listing/retrieving categories and MFOs, searching offers, fetching reviews, and providing market/legal context. Minor gaps exist (e.g., no dedicated tool to fetch a single specific offer by ID, or sort/filter categories beyond the provided criteria), but these are workable around using the existing tools.