Подбор предложений МФО по сумме (₽), сроку (дней) и признаку «первый займ под 0%» (first_loan_zero_percent: true/false/null, null = не подтверждено). Call without filters returns the full catalog (use limit); prefer passing amount/term for targeted results.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| amount | No | ||
| term_days | No | ||
| first_loan_zero | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the full-catalog behavior when unfiltered and explains the null semantics of first_loan_zero. However, it omits details about output format, pagination, or any side effects beyond reading.
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?
Two concise sentences deliver purpose, filter semantics, and usage guidance without any filler. The most important information is front-loaded.
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 4-parameter search tool with no output schema or annotations, the description covers the main filter dimensions, the unfiltered-call consequence, and the limit suggestion. It could further explain the limit parameter and return shape, but it is sufficient for confident 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?
With 0% schema description coverage, the description compensates by explaining amount (₽), term (days), and the first_loan_zero flag including its true/false/null meaning. The limit parameter is only referenced as a hint ('use limit') but not fully documented, leaving a small gap.
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 specifies that the tool selects MFO offers by amount, term, and the first-loan-zero flag. These distinct filter dimensions differentiate it from sibling read-only tools like get_mfo or list_categories.
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?
It explicitly warns that calling without filters returns the full catalog and advises using limit, and recommends filtering by amount/term for targeted results. It doesn't list alternative tools, but the guidance is clear enough for basic usage.
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.
Each tool has a distinct primary function: listing vs. retrieving single entities, searching offers, and retrieving rules/reviews. The only potential ambiguity is between get_category (curated collections) and search_offers (parameter-based search), but their descriptions clarify the purpose.
All tool names follow a consistent verb_noun pattern: get_ for single items, list_ for collections, and search_ for query-based retrieval. No mixed conventions or vague verbs.
Seven tools is well-scoped for a read-only catalog server, covering all major resources without redundancy or bloat.
The surface covers the full domain: categories, MFO details, reviews, market rules, and search. As a read-only catalog, no CRUD operations are needed, and no obvious gaps exist.