Linked API

nv_retrieve_alerts

Read-only

Retrieve Sales Navigator lead and account alerts (root-only nv.retrieveAlerts). Returns a workflow acknowledgement; use get_workflow_result with operationName nvRetrieveAlerts. Final data is an array of alerts: id (notification URN), type (open upstream machine code), publishedAt (ISO UTC), subject {type: lead/account, urn, name: string|null, url, saved: boolean|null}, headline, text, subline, url, relatedEntityUrn (all five nullable strings). Subject URLs can be passed to nv_fetch_person or nv_fetch_company. Filters are ANDed. Saved-search and shared-list system notifications are excluded.

Linked API actions are queued into a cloud-browser workflow and may take several minutes. The server returns immediately after starting the workflow with {status: 'pending'|'running', pendingReason, workflowId, operationName, message}. To retrieve the final result, call get_workflow_result with the returned workflowId and operationName — it will long-poll until completion or the request budget elapses, then return either the final result or another in-progress snapshot. Do not retry the original tool while a workflow is still running; that creates duplicate queued work.

A pending workflow carries pendingReason: 'queued' means it is waiting its turn behind other work on the same account and will start within minutes. 'outsideWorkingHours' means the account has configured working hours and the workflow is parked until they reopen — possibly the next working day. In that case get_workflow_result returns immediately instead of polling, message states when the window opens, and you should report that to the user rather than looping.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "nv_retrieve_alerts"
  }
}

Input Schema

Name	Required	Description	Default
`sort`	No	Sales Navigator ordering; latest is newest first.	latest
`limit`	No	Maximum number of matching alerts to return.
`filter`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 6, 2026

addedInput schema / properties / filter / properties / listId

Added value: +{
+  "description": "Owned list ID. Requires latest sort. ANDed with the other filters.",
+  "pattern": "^[1-9]\\d*$",
+  "type": "string"
+}

addedInput schema / properties / filter / properties / subjects

Added value: +{
+  "description": "OR of recognised hashed URLs or Sales Navigator subject URNs; empty is unrestricted. Public handles cannot resolve subject identities. Other filters are ANDed.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

AddedNov 3, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only say readOnly and openWorld; the description adds the crucial non-obvious behaviors: the action is queued into a cloud-browser workflow, may take minutes, returns an immediate acknowledgement object with status/pendingReason/workflowId, retrying causes duplicate queued work, and working-hours configuration can park the job until the next working day. It also discloses an exclusion rule (saved-search and shared-list system notifications are dropped).

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 purpose and return shape, then the async lifecycle, then pendingReason variants — a sensible order. It is long, and the second and third paragraphs repeat the get_workflow_result/workflowId instruction, but with no output schema the field enumeration earns its space.

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?

With no output schema, the field-by-field return description is necessary and is supplied, and the async lifecycle plus pendingReason branches are covered fully. Gaps are minor: no mention of auth/seat prerequisites for root-only access, and no note on behaviour when limit exceeds available alerts or on malformed filter values.

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

Parameters3/5

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

Schema coverage is 67%, so the schema already documents most parameters (including listId's latest-sort requirement and the subjects OR/URN semantics). The description adds only the global rule that filters are ANDed and that subject URLs can be forwarded to nv_fetch_person/nv_fetch_company; it says nothing about sort, limit, types, or the interaction of category with subjects beyond the schema text.

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

Purpose5/5

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

Opens with a specific verb+resource ("Retrieve Sales Navigator lead and account alerts") and immediately scopes it ("root-only nv.retrieveAlerts"), then enumerates the returned alert fields. It also distinguishes related siblings by pointing subject URLs at nv_fetch_person/nv_fetch_company and completion at get_workflow_result, so an agent can tell it apart from other retrieval tools without opening a schema.

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?

Gives explicit follow-up procedure (call get_workflow_result with workflowId and operationName, which long-polls) and an explicit prohibition ("Do not retry the original tool while a workflow is still running"). It also tells the agent how to behave on pendingReason 'outsideWorkingHours' (report to user, don't loop). It does not compare against non-alert retrieval siblings such as nv_retrieve_lists, but the workflow usage is unusually well specified.

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

All Linked API 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.