Skip to main content
Glama

Send a job application (Bewerbung) by email

send_job_application
DestructiveIdempotent

Use this when the user has seen the draft of their job application (Bewerbung) and explicitly wants it sent. Sends exactly one email to the employer, with the cover letter and the user’s resume document or another PDF (anhang or datei) as attachment. The call is the user’s consent for exactly this job: make it only after they have seen the draft and explicitly asked to send it. A second call for the same job sends nothing and names the first application. Scope: bewerbung:senden.

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": {
      "stelleId": "<stelleId>",
      "anschreiben": "<anschreiben>"
    },
    "name": "send_job_application"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateiNoThe attachment as an attached PDF file.
anhangNo
stelleIdYes
anschreibenYes

Output Schema

NameRequiredDescriptionDefault
titelYes
anhangYes
betreffYes
stelleIdYes
empfaengerYes
gesendetAmYes
zustellungYes
arbeitgeberYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / datei
      Added value: +{
      +  "description": "The attachment as an attached PDF file.",
      +  "properties": {
      +    "download_url": {
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    "file_id": {
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    "file_name": {
      +      "type": "string"
      +    },
      +    "mime_type": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "download_url",
      +    "file_id"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / properties / eingewilligtAm
      Removed value: -{
      -  "format": "date-time",
      -  "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
      -  "type": "string"
      -}
    • addedOutput schema / properties / gesendetAm
      Added value: +{
      +  "format": "date-time",
      +  "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
      +  "type": "string"
      +}
    • removedOutput schema / properties / id
      Removed value: -{
      -  "format": "uuid",
      -  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      -  "type": "string"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "id",
      -  "stelleId",
      -  "titel",
      -  "arbeitgeber",
      -  "empfaenger",
      -  "betreff",
      -  "anhang",
      -  "eingewilligtAm",
      -  "zustellung"
      -]New value: +[
      +  "stelleId",
      +  "titel",
      +  "arbeitgeber",
      +  "empfaenger",
      +  "betreff",
      +  "anhang",
      +  "zustellung",
      +  "gesendetAm"
      +]
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes further by defining what idempotency means here ('a second call for the same job sends nothing and names the first application') and by requiring explicit user consent. What it omits is any statement of irreversibility (the email cannot be recalled) or delivery/error behavior.

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?

The precondition is front-loaded in the first sentence, which is right for a destructive tool. The consent rule is stated twice ('explicitly wants it sent' and 'The call is the user's consent'), costing a little efficiency, but nothing else is filler.

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?

An output schema and rich annotations exist, so the description needn't cover return values, and it correctly focuses on sequencing, consent, scope, and repeat-call behavior. The remaining gap is the unexplained anhang-versus-datei choice, which matters for a nested-object parameter set.

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 description coverage is only 25%, so the description must compensate and only partly does: it labels anschreiben as the cover letter and names anhang/datei as the PDF attachment, but never explains the difference between the two attachment shapes or documents stelleId. The base64 size/format constraints in the schema also go unremarked.

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: 'Sends exactly one email to the employer, with the cover letter and the user's resume document or another PDF as attachment.' The prerequisite of a reviewed draft implicitly separates it from draft_job_application, and 'exactly one email' fixes the scope precisely.

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?

Names the exact condition for use ('after they have seen the draft and explicitly asked to send it'), restates it as a consent rule, and even describes what happens on an improper repeat call. An agent has no ambiguity about when to fire this versus the draft sibling.

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