Democruit

Run company research

continue_company_research

Destructive

Confirm a pending company research request, choose the matching company candidate, or refresh saved research. Spends research allowance and requires conversation confirmation. Operations: confirm | select | refresh. Returns the response envelope; nextActions list what the user can do next, primary first. Use confirm: false for a preview, then repeat identical inputs with confirm: true and the preview confirmationToken after the user confirms.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operation": "<operation>",
      "confirm": "<confirm>"
    },
    "name": "continue_company_research"
  }
}

Input Schema

Name	Required	Description
`confirm`	Yes	Set to true only after the user has explicitly confirmed this action in the conversation. Describe what will change to the user first.
`confirmed`	No	The confirmed supplied by the user. Follow the type and allowed values in this schema.
`operation`	Yes	Choose the task. Each operation accepts only its own fields.
`researchId`	No	Optional when exactly one candidate item exists: omit its ID to use that item. Ask which saved item to use only when several exist.
`sectionIds`	No	The section ids supplied by the user. Follow the type and allowed values in this schema.
`candidateIndex`	No	The candidate index supplied by the user. Follow the type and allowed values in this schema.
`confirmationToken`	No	Token returned by the preview. Send it unchanged with confirm: true; it is valid for 15 minutes and only for the previewed inputs.

Output Schema

Name	Required	Description	Default
`data`	No
`page`	No
`error`	No
`links`	No
`status`	Yes
`notices`	No
`polling`	No
`summary`	Yes
`agentHint`	No
`nextActions`	Yes
`appliedDefaults`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 8, 2026

removedInput schema / allOf

Removed value: -[
-  {
-    "if": {
-      "properties": {
-        "operation": {
-          "enum": [
-            "confirm",
-            "select",
-            "refresh"
-          ]
-        }
-      },
-      "required": [
-        "operation"
-      ]
-    },
-    "then": {
-      "required": [
-        "confirm"
-      ]
-    }
-  }
-]

addedInput schema / properties / confirmationToken

Added value: +{
+  "description": "Token returned by the preview. Send it unchanged with confirm: true; it is valid for 15 minutes and only for the previewed inputs.",
+  "maxLength": 200,
+  "type": "string"
+}

AddedNov 8, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description adds meaningful context they do not: this operation spends research allowance and requires explicit conversation confirmation, plus the preview-then-confirm token pattern, which is exactly the kind of cost and consent information an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the three capabilities, then cost/consent constraints, then the operation list and the preview workflow. Dense but every sentence carries operational information; the explicit 'confirm | select | refresh' enumeration is slightly redundant with the enum in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, allowance-spending, seven-parameter tool this covers the essentials: cost, consent gate, preview flow, and operation set. An output schema exists so return values need not be described, though the mention of nextActions/response envelope is a useful bonus.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3, but the description adds real meaning on top: it explains the confirm: false versus confirm: true progression and that the confirmationToken must come from the preview and be reused with identical inputs. The researchId single-candidate omission rule is only in the schema, not the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (company research) with three named verbs (confirm, select, refresh) and enumerates the operation values, so an agent can map intent to operation. It does not contrast with the sibling research_company tool, leaving the boundary between starting new research and acting on a pending request implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete two-step workflow: call with confirm: false for a preview, then repeat identical inputs with confirm: true plus the preview confirmationToken after the user confirms. What is missing is when to pick select versus refresh, and when to prefer research_company over this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Democruit tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?