Default company call: one-shot web + firmographics + domain trust by name or domain. Use lion_company_enrich if you only need name/employees/country. Use lion_verified_company_file for KYB source trail. $0.03 Base USDC. [x402 paid: GET /api/x402/company-research]
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Company name or domain e.g. stripe.com | |
| domain | No | Optional domain override |
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 does not describe side effects, safety, authentication requirements, rate limits, or what happens to data. While it mentions the cost and paid endpoint, it omits critical behavioral details such as whether this is a read-only operation, what the response format is, or any error conditions. The 'one-shot' term is ambiguous. 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 compact and front-loaded with the main purpose, followed by explicit routing to alternatives and pricing/endpoint info. Every clause serves a purpose: differentiation, pricing, and alternative routing. However, it could be slightly more structured (e.g., a clear separation of 'what it does' vs 'how to pay'), but as a single paragraph it is efficient and readable.
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 there is no output schema, the description should explain what the tool returns or at least the nature of results. It mentions 'web + firmographics + domain trust' but doesn't specify the output format, pagination, or error behavior. It also lacks explanation of what 'one-shot' means. The cost and paid endpoint are useful, but the absence of return-value description makes the tool incomplete for an agent, especially with no schema or annotations to fill the gap.
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% for both parameters (q and domain), so the schema already documents them. The description mentions 'by name or domain' which aligns with q but adds no additional meaning beyond what the schema provides. The optional domain override is also self-explanatory from the schema. Baseline 3 is appropriate when schema does the heavy lifting and the description adds little extra semantic value.
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 performs company research combining web data, firmographics, and domain trust, and it explicitly differentiates from sibling tools lion_company_enrich and lion_verified_company_file. The verb 'call' and resource 'company' are clear, and the 'Default company call' phrase sets it as the primary option. This is a specific and distinguishable purpose.
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?
Explicit usage guidance is provided: 'Use lion_company_enrich if you only need name/employees/country' and 'Use lion_verified_company_file for KYB source trail.' This tells the agent exactly when to choose alternatives, covering both the main use case and exclusions. Nothing is left to inference.
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 clearly defined purpose with explicit usage notes, e.g., lion_company_enrich is firmographics-only while lion_company_research adds web data, and lion_verified_company_file provides a full source trail. Even overlapping tools like wallet_screen and multi_sanctions_bundle are scoped by input type and desired output, leaving no ambiguity.
All tools follow a strict 'lion_' prefix with snake_case descriptive names (e.g., lion_company_enrich, lion_wallet_screen). The verb-noun pattern is consistent across the set, making it predictable and easy to navigate.
With exactly 8 tools, the server is well-scoped for its stated purpose of x402 data and RPC. The count is neither bloated nor thin, and each tool addresses a distinct use case from quick intel to full compliance bundles.
The tool surface covers the full lifecycle of company and Sanctions screening: free tier (quick_intel, declare_need), enrichment, research, sanctions (wallet_screen, multi_sanctions_bundle), and verified KYB (verified_company_file). No obvious gaps like missing update/delete actions exist, and all core workflows end in a paid path without dead ends.