Skip to main content
Glama

Start outreach to people

requestOutreach
Destructive

Start email and LinkedIn outreach from Clera, for one of your roles, to people found outside Clera's network. This SENDS REAL MESSAGES.

Without searchId it covers everyone on that role's People Search shortlist. With searchId (from searchExternalTalent) it covers every visible person in that search, up to 500. People without a LinkedIn profile are skipped.

Clera drops people who opted out, are already in Clera's network (use requestIntro for those) or were contacted recently, finds emails and writes a personal opener, then sends on its own. There is no fit check: everyone the user picked is contacted. Replies land in the company's pipeline. One open request per role; check listOutreachRequests first.

Resolve jobId yourself with the job tool's list command; never ask the user for an id. Tell the user the role and how many people will be contacted and get an explicit yes before calling.

Clera privately records this tool's inputs and results for usage tracking and support.

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": {
      "jobId": "<jobId>"
    },
    "name": "requestOutreach"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYesThe role the outreach is for.
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
searchIdNoAn external search id from searchExternalTalent. Omit to use the role's shortlist instead.

Output Schema

NameRequiredDescriptionDefault
scopeYes
statusYes
createdAtYes
requestIdYes
roleTitleYes
talentCountYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the annotations by naming what gets destroyed/irreversible in practice: real messages are sent, there is no fit check, one open request per role, people without LinkedIn or who opted out are skipped, and emails are discovered plus a personal opener written. The destructiveHint and openWorldHint annotations are fully corroborated rather than merely restated.

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 highest-stakes fact (this SENDS REAL MESSAGES) and organized by scope, filtering, and prerequisites. Dense but nearly every sentence carries operational value; the closing privacy line is boilerplate but brief.

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 destructive, open-world, non-idempotent tool, it covers eligibility filtering, deduplication, concurrency limits, prerequisite checks, and confirmation requirements. An output schema exists, so return values need not be spelled out.

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?

Even at 100% schema coverage the description adds meaning the schema lacks: the 500-person cap for searchId, that people without a LinkedIn profile are skipped, and explicit instruction to resolve jobId with the job tool's list command rather than asking the user. This meaningfully changes how the parameters get populated.

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?

States a specific verb and resource (start email and LinkedIn outreach), names the scope (one of your roles, people outside Clera's network), and explicitly contrasts with requestIntro. An agent can distinguish it from siblings without opening schemas.

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?

Gives explicit when-to-use branches: omit searchId to cover the role's shortlist, supply searchId from searchExternalTalent to cover a search, and use requestIntro for people already in Clera's network. Adds prerequisite sequencing (check listOutreachRequests first, resolve jobId yourself, get an explicit yes).

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.

Resources