Detects "shell-firm hotel" patterns — counts how many companies share the same registered address. Threshold-based risk: 1-9 normal (multi-tenant office), 10-49 mild (legitimate coworking), 50-199 medium (virtual office provider), 200+ high (shell-firm hotel). Compliance tier or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| ico | Yes | Czech IČO 7-8 digits |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds valuable behavioral context: it explains the threshold-based risk classification (1-9, 10-49, 50-199, 200+) and notes the compliance tier requirement, which is not covered by annotations. It does not contradict the read-only hint as 'detects' and 'counts' are read operations.
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 and front-loaded, starting with the tool's main function. Each sentence provides necessary detail: the definition, the thresholds, and the access requirement. There is no unnecessary repetition or filler.
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?
For a simple tool with one parameter, read-only annotations, and no output schema, the description is nearly complete. It explains the detection logic and thresholds, and includes the compliance tier requirement. It could be more explicit about the return format (e.g., whether it returns a count, a risk category, or both), which would be helpful given the lack of an output schema.
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 for the single parameter (ico) is 100%, as the schema already describes it as 'Czech IČO 7-8 digits'. The description adds no additional information about the parameter itself, so it does not go beyond the schema. The baseline for high coverage is 3.
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 what the tool does: 'Detects shell-firm hotel patterns — counts how many companies share the same registered address.' This is a specific verb+resource with additional detail on the pattern. It differentiates itself from sibling detection tools by focusing on address crowding.
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 provides context on the tool's purpose and includes a threshold-based risk interpretation, which implies when it would be relevant. However, it does not explicitly state when to use this tool versus sibling tools like detect_nominee_director or detect_phoenix, nor does it mention any exclusions. The 'Compliance tier or higher' requirement is a usage constraint but not an explicit when/when-not guideline.
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.
Most tools have clearly distinct purposes: address crowding, nominee directors, phoenix patterns, owners, statutory chains, timelines, and watch functionality are all separate. However, get_dd_report and get_risk_score overlap significantly (full report vs. just the score), and the three detect_* tools share a similar pattern but apply to different risk types.
Tool names predominantly follow a verb_noun pattern (detect_, get_, watch_), but person_companies breaks this convention (noun_noun). The mix of detect_ and get_ verbs is consistent within their respective semantic groups, making the overall pattern readable.
With 12 tools, the server is well-scoped for a due-diligence domain. Each tool addresses a distinct aspect (risk detection, reports, ownership, monitoring) without unnecessary bloat, and the count sits comfortably within the ideal range.
The server covers the core due-diligence lifecycle reasonably well: company facts, risk scoring, timeline, ownership, EU lookup, and monitoring onboarding. Minor gaps exist—watch_entity is a stub, and advanced features are explicitly deferred to a companion server (ddplus)—but these are acknowledged and don't break the primary workflows.