get_requirementsGet the exact questions to ask the user for a given document type and country, with validation rules and legal constraints. You MUST use these questions verbatim as your source of truth for the interview — do not invent fields. Fields are ordered and may be conditional on previous answers.
| Name | Required | Description | Default |
|---|---|---|---|
| country | Yes | ||
| language | No | ||
| document_type | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description reveals key behavioral traits: questions must be used verbatim, fields are ordered, and they may be conditional on previous answers. This adds significant context for safe invocation.
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 sentences, front-loaded with the core purpose, and each sentence provides necessary behavioral detail. No filler or redundant rephrasing.
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?
Despite no output schema, the description adequately conveys what is returned (questions with validation and legal constraints), how to use them, and structural nuances (ordering, conditionality). Enough for an agent to understand the tool's role.
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 description mentions document_type and country, reinforcing their roles, but does not explain the optional language parameter. With 0% schema description coverage, the description should compensate more fully for all parameters.
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 retrieves 'exact questions to ask the user' for a given document type and country, with validation rules and legal constraints. This specific verb+resource combination distinguishes it from siblings like generate_document or list_document_types.
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?
Strong guidance: the tool is positioned as the 'source of truth' for the interview, with explicit instruction to use questions verbatim and not invent fields. It doesn't explicitly name alternatives but the context and imperative tone make usage clear.
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 unique role in the document creation pipeline: list_document_types for discovery, get_requirements for gathering inputs, generate_document for drafting, purchase_document for buying, and get_document_status for tracking. No two tools overlap in purpose, minimizing misselection risk.
All tool names follow a consistent verb_noun snake_case pattern: generate_document, get_document_status, get_requirements, list_document_types, purchase_document. The verbs are clear and predictably structured.
Five tools is well-scoped for a legal document generation service, covering the essential workflow without unnecessary additions. The count feels natural for the domain and avoids bloat.
The tools cover the full user journey: discover available document types, fetch required questions, generate a draft, purchase the final document, and check order status. No critical step in the core workflow is missing, making the set functionally complete.