Генерация коммерческого предложения (КП) на бассейн «под ключ». 12 разделов: бассейн, фильтрация, нагрев, автоматика, очистка, освещение, дезинфекция, покрытие, фитинги, монтаж, работы, доставка
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | Город клиента (для дилера и доставки) | |
| model | Yes | Модель: laguna2..laguna9 | |
| extras | No | Доп. опции | |
| series | No | Серия: premium или nord | |
| client_name | No | ФИО клиента |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden of behavioral disclosure. It only states that a proposal is generated and lists sections, but does not reveal side effects, return format, required permissions, or whether the proposal is simply returned or persisted. This is a significant gap for a tool with no annotation support.
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, concise sentence that front-loads the main purpose and provides a useful enumeration of the 12 sections. No filler or redundant content.
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 (nested extras, multiple options, no output schema) and lack of annotations, the description is insufficient. It does not explain what the returned proposal looks like, that model is required, or how it relates to sibling tools like send_kp_email. The description only offers a high-level overview without operational details.
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 100%, so the baseline is 3. The tool description adds contextual context by listing the proposal sections, which loosely map to parameters like extras, but it does not explain how parameters affect the output or clarify the nested extras structure beyond what the schema already describes.
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 explicitly states the tool generates a commercial proposal (КП) for a turnkey pool, and lists the 12 included sections. This clearly identifies the action and resource, distinguishing it from siblings like send_kp_email (which sends) and calculate_total (which calculates totals).
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 does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives like send_kp_email or get_pool_price. The intended usage is implied by the tool name and description but not stated, leaving the agent to infer when this tool should be selected over related tools.
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.
Several tools have overlapping purposes: get_architect_package and get_bim_files both provide BIM/CAD resources, generate_kp and calculate_total both compute pricing, and search_pools and recommend_pool both guide pool selection. The detailed descriptions help differentiate them, but the boundaries are not always crisp.
Most tools follow a verb_noun snake_case pattern (get_price, send_email, search_pools). Minor deviations like tech_consult (adjective-noun) and consult_service (verb then noun, but technically 'consult' is the verb) are slight outliers, but the overall convention is consistent and readable.
With 21 tools, the server sits in the heavy range. While the domain is broad (product info, quotes, consultations, catalogs, architectural resources), several get_* catalog tools (filters, accessories, furniture, slides) could potentially be consolidated, and list_tools adds little functional value. The count is borderline appropriate.
The tool surface covers the main sales flow (search, recommend, specs, pricing, quote generation/email, dealer lookup, lead submission) plus post-sale support (service consultation, repair services, pool passport, technical consultation). Minor gaps exist, such as no tool for scheduling maintenance or tracking lead status, but the core domain is well covered.