Skip to main content
Glama

rc_send_message

Send Message in Recruiter Lite. Requires a LinkedIn Recruiter Lite seat and Linked API's Plus plan. Use personUrl from recruiterProfileUrl in rc_search_people or rc_retrieve_project_candidates, or personRecruiterUrl in get_inbox. New InMail requires personUrl, subject (1–200 characters, one line) and text (1–1900 characters). Reply with threadId from get_inbox and text only, without personUrl or subject. A paid InMail credit is spent only when allowPaidCredit is true. Turn on allowPaidCredit only when the user has explicitly approved spending a paid InMail credit on this message; on inMailCreditRequired, ask the user instead of retrying with allowPaidCredit on. After an unexpectedError, check the conversation before sending again. Final result: { creditUsed }.

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": "rc_send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
subjectNo
threadIdNo
personUrlNoRecruiter profile URL (https://www.linkedin.com/talent/profile/…) from recruiterProfileUrl in rc_search_people or rc_retrieve_project_candidates, or personRecruiterUrl in get_inbox; public /in/ URLs are not accepted
allowPaidCreditNoA paid InMail credit is spent only when this is true; default false. Turn on allowPaidCredit only when the user has explicitly approved spending a paid InMail credit on this message; on inMailCreditRequired, ask the user instead of retrying with allowPaidCredit on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the material behavior: the action is queued into a cloud-browser workflow that may take minutes, the immediate return is a pending snapshot with pendingReason/workflowId, and final results must be fetched via get_workflow_result. It further discloses the paid-credit cost model, the inMailCreditRequired error path, and duplicate-work risk from retrying.

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?

Well front-loaded: purpose and prerequisites, then parameter sourcing, then error/credit policy, then the async workflow model. It is long, and the workflow paragraph could be tightened, but each paragraph carries information an agent needs to avoid duplicate sends or unapproved credit spend.

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?

For a complex, costly, asynchronously-executed mutation with no output schema, the description supplies the pending-response shape, the meaning of each pendingReason (queued versus outsideWorkingHours), the retrieval path via get_workflow_result, and the final result shape ({ creditUsed }). Nothing essential to correct invocation is missing.

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

Parameters5/5

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

With only 40% schema description coverage, the description carries the parameter burden well: it names the accepted source of personUrl (recruiter profile URLs, not public /in/ URLs), the source of threadId (get_inbox), the mode-dependent exclusivity of personUrl/subject versus threadId, and the approval policy governing allowPaidCredit. Only the length/format constraints on subject and text duplicate the schema.

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 Message') and scopes it to Recruiter Lite, which implicitly separates it from the generic send_message / nv_send_message. It does not explicitly name the non-Recruiter alternative, so the sibling differentiation is contextual rather than spelled out.

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 distinguishes two modes: a new InMail (personUrl + subject + text) versus a reply (threadId + text, without personUrl or subject), and tells the agent exactly where each identifier comes from (rc_search_people, rc_retrieve_project_candidates, get_inbox). It also states when-not conditions: do not enable allowPaidCredit without user approval, do not retry on unexpectedError before checking the conversation, and do not retry while a workflow is running.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.