Xynaptic Company Search — find French companies by name or SIREN: identity, activity, status. The entry point to the company funnel. Parameter: ?q=name. [price: $0.005 per call, x402/USDC]
| Name | Required | Description | Default |
|---|---|---|---|
| params | No | query parameters |
Changes observed during successful MCP inspections.
Input schema / properties / bodyRemoved value: -{
- "description": "JSON body for POST endpoints (e.g. insurance, ai-chat, production-risk)",
- "type": "object"
-}Input schema / properties / params / descriptionPrevious value: -"query parameters, e.g. {city: 'Paris', type: 'Appartement'}"New value: +"query parameters"Input schema / properties / params / propertiesAdded value: +{
+ "query": {
+ "description": "example: \"michelin\"",
+ "type": "string"
+ },
+ "results": {
+ "description": "example: 3",
+ "type": "number"
+ },
+ "top": {
+ "description": "example: {\"siren\":\"424622884\",\"name\":\"MICHELIN\"}",
+ "type": "string"
+ }
+}Input schema / requiredAdded value: +[]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose a meaningful behavioral trait: the paid access model ($0.005 per call, x402/USDC), which an agent needs to know before invoking. It does not cover auth, rate limits, or the shape of results, leaving gaps for a no-annotation tool.
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, front-loaded with the verb and resource; the funnel position and price each earn their place. The embedded '?q=name' pseudo-parameter and bracketed price are slightly noisy but do not bury the main point.
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?
Covers purpose, positioning, and cost, but with no output schema and no annotations the description should say more about what a match list contains (SIREN, name, status), pagination, and what the 'top'/'results' parameters control. Nested-object params make this gap more consequential.
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 nominally 100%, but the schema descriptions are only raw examples, so baseline 3 applies. The description's hint '?q=name' adds a query-by-name cue but is syntactically inconsistent with the schema property named 'query', and it says nothing about 'top' or 'results'.
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?
Names a specific verb and resource ('find French companies by name or SIREN') and enumerates the fields returned (identity, activity, status). The 'French' qualifier implicitly distinguishes it from company-international-search, though no sibling is named explicitly.
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 phrase 'The entry point to the company funnel' implies this is the first step before profile/financial/KYB lookups, which is useful positional guidance, but there is no explicit when-to-use statement and no when-not or named alternative.
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.