Firmographics only (name, employees, country, industry, website). Not a web-research pack — use lion_company_research for that. $0.04 Base USDC. [x402 paid: GET /api/x402/company-enrich]
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | ||
| fields | No | Comma-separated fields | |
| format | No | apollo_org for drop-in shape | |
| identifier | Yes | Company name or domain |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It earns credit for revealing the paid model and endpoint ('$0.04 Base USDC. [x402 paid: GET /api/x402/company-enrich]'), which is useful cost context. However, it doesn't disclose failure behavior, permission/auth requirements beyond payment, or output shape — meaningful gaps given zero annotation coverage.
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?
Four short clauses with zero filler, purpose front-loaded first, routing second, and cost/endpoint last. Every sentence earns its place, and the pricing line is information an agent needs before committing to a paid call.
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?
With no output schema and no annotations, the burden falls on the description. It adequately covers selection and cost, but omits invocation specifics (the identifier-vs-domain usage question) and gives no hint of the return contract. Adequate for routing, incomplete for a first-time caller executing the call without further digging.
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 coverage is 75% (fields and format have descriptions; domain has none), so the schema does most of the work on documented params. But the description adds nothing about parameters and fails to resolve the inherent identifier-vs-domain ambiguity: identifier accepts 'name or domain' per schema, yet domain is a separate field — the description never clarifies when to use which, leaving a real invocation risk for the one required param.
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?
States a specific verb and resource with a concrete output scope: 'Firmographics only (name, employees, country, industry, website).' This precisely delimits what the tool returns and names the sibling it is not ('use lion_company_research for that'), leaving no ambiguity about the tool's role.
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?
Explicitly excludes the web-research alternative ('Not a web-research pack — use lion_company_research for that') and implies the selection condition through 'Firmographics only.' It doesn't fully enumerate when-not-to-use scenarios against the other six siblings, but the primary routing decision is crisply handled.
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.
Tools are largely distinct: enrich provides basic firmographics, research adds web intel, compliance bundle combines sanctions with domain data, wallet screen checks addresses, multi-sanctions covers broader lists. Some overlap exists between research/enrich/verified_file and between sanctions tools, but descriptions explicitly cross-reference when to use each. declare_need serves as a router to reduce ambiguity.
All tools follow a consistent 'lion_' prefix with snake_case. Names are descriptive nouns or noun phrases (company_enrich, compliance_bundle, wallet_screen) rather than a strict verb_noun pattern, but the naming is uniformly structured and predictable. Minor deviation: lion_declare_need uses a verb, but the prefix and formatting remain consistent across the entire set.
With 8 tools, the count falls well within the ideal 3-15 range. Each tool serves a distinct paid or free purpose in the company/compliance workflow, from lightweight enrichment to full attested dossiers and sanctions screening. No redundancy or missing essential function that would require adding or removing tools.
The tool surface covers the full lifecycle of company and compliance data needs: free teaser (quick_intel), basic enrichment, detailed research, sanctions screening (single and multi-list), a comprehensive compliance bundle, and a fully attested KYB dossier. The free router (declare_need) also helps agents navigate to the correct paid path, closing the gap of 'which tool do I start with'. No obvious missing operations for a read-only data provider.