Start an async OSINT investigation for a domain. Operator-deploy only; targets must be operator-authorized on the recon watchlist; degrades to info when unprovisioned. Returns an investigationId immediately — poll with osint_investigation_status and retrieve results with osint_investigation_report.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Investigation subject, per tool: a domain, public IP, organisation name, email address or username. |
Changes observed during successful MCP inspections.
Input schema / properties / query / descriptionAdded value: +"Investigation subject, per tool: a domain, public IP, organisation name, email address or username."Output schema / (root)Previous value: -{
- "additionalProperties": {},
- "properties": {
- "category": {
- "type": "string"
- },
- "findings": {
- "items": {
- "additionalProperties": {},
- "properties": {},
- "type": "object"
- },
- "type": "array"
- },
- "passed": {
- "type": "boolean"
- },
- "score": {
- "type": "number"
- }
- },
- "required": [
- "category",
- "score",
- "passed",
- "findings"
- ],
- "type": "object"
-}New value: +nullInput schema / additionalPropertiesAdded value: +falseOutput schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": {},
+ "properties": {
+ "category": {
+ "type": "string"
+ },
+ "findings": {
+ "items": {
+ "additionalProperties": {},
+ "properties": {},
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "passed": {
+ "type": "boolean"
+ },
+ "score": {
+ "type": "number"
+ }
+ },
+ "required": [
+ "category",
+ "score",
+ "passed",
+ "findings"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite annotations already covering safety hints, the description adds meaningful behavior: the investigation is asynchronous, returns an investigationId immediately, requires operator authorization, and degrades to informational output when unprovisioned. This gives an agent the operational context needed to invoke it correctly.
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 three focused sentences, front-loading the purpose, then constraints, then the async return and follow-up workflow. There is no redundant or filler content.
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 an async start tool with no output schema, the description covers the immediate return value, the polling tool, the reporting tool, authorization requirements, and provisioning behavior. An agent has enough information to call it and continue the workflow.
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?
There is only one parameter and schema coverage is 100%, so the schema already fully documents it. The description confirms the expected subject is a domain, but does not add syntax or format constraints beyond the schema.
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 states a specific verb and resource: start an async OSINT investigation for a domain. The domain qualifier distinguishes it from sibling start tools such as osint_investigate_email_start and osint_investigate_username_start.
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?
It clearly states usage constraints: operator-deploy only, targets must be operator-authorized on the recon watchlist, and provisioning degrades to info. It also names the follow-up tools for polling and reporting, but it does not explicitly contrast this with alternative investigation or scanning tools.
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.