Linked API

send_message

Allows you to send a message to a person (st.sendMessage action). Provide either personUrl or threadId (threadId replies into an existing conversation thread and takes precedence). Optionally pass manageConversation to archive, star, or mute the conversation right after the message is sent (chained st.manageConversation child, acting on the same thread). If this workflow is still running, do not retry this tool; retrying can send duplicate messages to the same person.

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

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": {
      "text": "<text>"
    },
    "name": "send_message"
  }
}

Input Schema

Name	Required	Description
`text`	Yes	The message text, must be up to 1900 characters.
`threadId`	No	Optional conversation thread identifier to reply into, as returned by get_inbox. Provide this instead of personUrl to reply directly into a known thread.
`personUrl`	No	LinkedIn URL of the person you want to send a message to (e.g., 'https://www.linkedin.com/in/john-doe'). Optional if threadId is provided.
`manageConversation`	No	Optional. Manage the conversation right after the message is sent. Acts on the same thread, so no threadId is needed.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond readOnlyHint=false and openWorldHint=true, the description discloses that execution is asynchronous via a cloud-browser workflow, may take several minutes, returns an immediate pending snapshot with a defined shape, and that retrying creates duplicate queued work or duplicate messages. It further explains pendingReason values including 'outsideWorkingHours' parking and how to report that to the user. The remaining gap is only around validation/failure modes of the send itself.

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

Conciseness3/5

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

The core action and addressing rule are front-loaded in the first sentence, which is good structure. However, the definition runs four dense paragraphs and repeats the no-retry-while-running warning twice verbatim in substance, and the long-poll/workflow mechanics are explained at greater length than selection of this tool requires.

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

Completeness5/5

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

Despite having no output schema, the description documents the returning envelope (status, pendingReason, workflowId, operationName, message) and the follow-up tool needed to resolve it, so an agent knows exactly what comes back. Combined with the addressing rules and async behavior, nothing material is missing for correct invocation.

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 coverage is 100%, so the baseline is 3, but the description adds the threadId-over-personUrl precedence rule and clarifies that manageConversation acts on the same thread so no threadId is needed, which the schema only hints at. It does not restate the 1900-character limit or other per-field detail, which is appropriate since the schema covers them.

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?

States a specific verb and resource ('send a message to a person') and immediately scopes the two addressing modes, distinguished by personUrl vs threadId. It also clarifies that manageConversation is a chained child acting on the same thread, which separates the embedded option from the standalone manage_conversation sibling. It stops short of naming a sibling alternative (e.g. nv_send_message or reply_to_comment) for related intents, so it is clear but not fully sibling-differentiated.

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

Usage Guidelines5/5

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

Explicitly states the two ways to address a recipient, the precedence rule when both are supplied, and when to use the optional manageConversation. It also gives negative guidance with alternatives: do not retry while a workflow runs, and call get_workflow_result with the returned workflowId/operationName instead. That covers when-to-use, when-not-to-use, and the follow-up path.

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.