Skip to main content
Glama

FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT

Create a job alert

job_alert_subscribe
DestructiveIdempotent

Subscribes the authenticated user to job alerts for a specific saved job search.

Input:

  • job_search_id: The job search identifier to subscribe to (required). Accepts either the job search UUID or the composite job ID returned by jobs_search / jobs_details (format: "seo_id--job_search_id").

  • delivery: digest, fast (optional). Fast email is not available on every account and needs enough new matches for the exact saved search. Unsupported fast selection returns a validation error and keeps the existing delivery mode.

  • frequency: Alert frequency — one of daily, weekly, monthly (optional, defaults to "weekly")

Output: Returns the created or updated job alert with id, status, and frequency, beside the user's current job alerts in the same shape and order as the first page of job_alert_list. Idempotent: calling this tool for an already-subscribed search updates the existing alert without creating a duplicate. An existing active alert with the same query text, location, company and filters, and at least the same radius, is returned instead of a new one, with the requested frequency applied to it. A user keeps one alert per query and place. When they already have an active alert for the same query and place with other filters, radius or sort, this tool changes that alert to the new search instead of adding a second one: the returned jobAlert.id is the existing alert, jobSearchId is the new search, and message says the alert was changed.

Delivery: Digest alerts arrive together in one email, one section per query and place. Opted-in fast alerts are sent separately while the account has them: matches found overnight arrive in one morning email at the hour the user usually starts the day, and later matches follow at least 3 hours after the previous email, up to 3 emails per local day. A fast email carries only jobs found since the previous one, never a job already sent to the user, a role from the same employer sent in the last 30 days, or a job in the user's tracker. When the account no longer has fast alerts they return to the ordinary digest and retain the saved fast preference. Each section applies every filter and the sort of its saved search, the same way jobs_search does for that account. A job appears in the digest once, even when it matches several alerts, and no email is sent when there are no new matches. The digest follows the most frequent alert, and arrives less often when the user has not used FoundRole for a while.

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": {
      "job_search_id": "<job_search_id>"
    },
    "name": "job_alert_subscribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
deliveryNoDelivery mode: digest, fast; fast is not available on every account and needs a qualifying search
frequencyNoAlert frequency: daily, weekly, monthly (defaults to "weekly")
job_search_idYesJob search UUID or composite job id ("seo_id--job_search_id") from jobs_search results

Output Schema

NameRequiredDescriptionDefault
hasMoreNo
jobAlertNo
jobAlertsNo
totalCountNo
frequenciesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / properties / frequencies
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / hasMore
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / jobAlerts
      Added value: +{
      +  "items": {
      +    "properties": {
      +      "createdAt": {
      +        "type": "string"
      +      },
      +      "delivery": {
      +        "type": "string"
      +      },
      +      "fastActive": {
      +        "type": "boolean"
      +      },
      +      "frequency": {
      +        "type": "string"
      +      },
      +      "id": {
      +        "type": "string"
      +      },
      +      "jobSearch": {
      +        "type": [
      +          "object",
      +          "null"
      +        ]
      +      },
      +      "lastSentAt": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "status": {
      +        "type": "string"
      +      },
      +      "subscriptionSource": {
      +        "type": "string"
      +      },
      +      "updatedAt": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "id"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / totalCount
      Added value: +{
      +  "type": "integer"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / delivery
      Added value: +{
      +  "description": "Delivery mode: digest, fast; fast is not available on every account and needs a qualifying search",
      +  "type": "string"
      +}
    • addedOutput schema / properties / jobAlert / properties / delivery
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / jobAlert / properties / fastActive
      Added value: +{
      +  "type": "boolean"
      +}
  3. Added
  4. Removed
  5. Changed3 schema fields changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedOutput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  6. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "jobAlert": {
      +      "properties": {
      +        "frequency": {
      +          "type": "string"
      +        },
      +        "id": {
      +          "type": "string"
      +        },
      +        "jobSearchId": {
      +          "type": "string"
      +        },
      +        "status": {
      +          "type": "string"
      +        },
      +        "subscriptionSource": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "id"
      +      ],
      +      "type": "object"
      +    }
      +  },
      +  "type": "object"
      +}
  7. Changed1 schema field changed
    • changedInput schema / properties / frequency / description
      Previous value: -"Alert frequency: \"daily\", \"weekly\", or \"monthly\" (defaults to \"weekly\")"New value: +"Alert frequency: daily, weekly, monthly (defaults to \"weekly\")"
  8. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare idempotentHint=true and destructiveHint=true; the description adds substantial context: idempotent update semantics, one-alert-per-query-and-place rule, fast-mode validation error fallback, and delivery cadence. It does not explain what 'destructive' means here or permission requirements, leaving a minor gap.

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?

Front-loads input/output and idempotency rules effectively, but the Delivery section runs long with email cadence, suppression rules, and digest timing that are well beyond invocation needs.

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?

Covers inputs, outputs, idempotency, conflict resolution, and delivery behavior for a three-parameter mutation tool. An output schema exists, so the lengthy return-value description is somewhat redundant but not harmful.

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%, but the description adds meaning: the composite job_search_id format from jobs_search/jobs_details, the fast-mode eligibility constraint and error behavior, and the frequency default. This is additive rather than repeating the schema.

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—subscribing the authenticated user to job alerts for a saved job search—and distinguishes it from siblings like job_alert_unsubscribe and job_alert_list.

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?

Explains the key when-behavior: an existing active alert for the same query and place is reused or changed rather than duplicated, with the returned id and message indicating which. It does not explicitly contrast with job_alert_unsubscribe or other siblings.

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.