Natural-language contractor search. Pass a free-form Russian brief (e.g. "хочу каркасный дом 180 кв.м в Подмосковье до 15 млн") and get top-N matching contractors plus an explanation of how the brief was parsed.
Returns JSON with: parsed filters, matches list, explanation.
| Name | Required | Description | Default |
|---|---|---|---|
| brief | Yes | ||
| top_n | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses the input (brief, top_n) and output (parsed filters, matches, explanation). It does not mention side effects, rate limits, or authentication requirements, but given that the tool likely performs a read-only search, the description is adequate.
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 concise: two sentences with no superfluous words. It front-loads the purpose, includes an example, and specifies output format. Every part is necessary and informative.
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 tool's complexity (NLP search) and the presence of an output schema, the description provides sufficient context. It explains the input, output structure, and example. The output schema exists to document return values, so the description does not need to elaborate on them.
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 0%, so the description must compensate. The description explains the 'brief' parameter with a detailed example and format (free-form Russian). It implicitly defines the 'top_n' parameter by mentioning 'top-N matching', but it does not specify the default value or expected range. This is a minor 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 states the tool's purpose: natural-language contractor search. It provides a concrete example of a Russian brief and specifies the output (parsed filters, matches, explanation). This distinguishes it from sibling tools like search_companies (structured search) and contractor_recommendation (likely recommendation-based).
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 explicitly instructs the user to pass a free-form Russian brief. It does not provide explicit exclusions or alternatives, but the context of siblings implies when this tool is appropriate (natural language queries) versus structured searches. A clear 'when not to use' statement would improve this dimension.
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.
Multiple tools have overlapping purposes: search_companies, find_best_companies, smart_match, and contractor_recommendation all find contractors; get_company, company_portfolio, and company_deep_profile all return company details; calculate_cost and project_estimator both estimate costs. This makes it difficult for an agent to reliably choose the correct tool.
Tool names mix verb-first patterns (get_*, search_*, compare_*, calculate_*, export_*, find_*, request_*) with noun-first patterns (company_deep_profile, market_report, price_comparison, etc.). All names use snake_case, but the inconsistent verb/noun placement makes the set less predictable.
24 tools falls squarely in the 16-25 'feel heavy' range. While the server covers a broad domain (companies, projects, analytics, leads, estimation), the presence of many overlapping tools suggests the count could be consolidated without losing functionality.
The toolset covers the core domain well: searching companies and projects, retrieving full details, comparing entities, estimating costs, obtaining market analytics, and managing the lead lifecycle (request_quote -> get_lead_status). Minor gaps exist (e.g., no detailed per-review text, but that is explicitly stated as unavailable), but there are no dead ends for typical workflows.