falzmarke

email_setzen

Typesets Markdown email content into output files and measures each result against target dimensions, so layout issues are caught before a mail program sends it.

Instructions

Setzt die E-Mail-Fassung und misst sie nach.

nachricht Markdown mit Frontmatter — der Text selbst, nicht ein Pfad. Das Frontmatter muss typ: email tragen. profil Name eines Profils auf dem Server oder ein ganzes Profil-Objekt. Fehlt beides, gilt das im Frontmatter genannte. als "pfad" (Vorgabe) oder "base64". ziel Wohin die Dateien sollen. Ohne Angabe in ein Temporärverzeichnis, das stehen bleibt — der zurückgegebene Pfad muss gültig sein. mit_quelle Die Markdown-Quelle als eigener Teil (ADR 0034, Punkt 3). Vorgabe ist ohne: Der Teil macht sichtbar, was im Brief nicht sichtbar wäre.

Es wird nichts versendet. Das Ergebnis sind Dateien; ob und wann sie jemand abschickt, entscheidet ein Mailprogramm (ADR 0034). Der Messbericht aus verify --email ist immer dabei — dieselbe Zusage wie beim Brief.

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": {
      "nachricht": "<nachricht>"
    },
    "name": "email_setzen"
  }
}

Input Schema

Name	Required	Default
`als`	No	pfad
`ziel`	No
`profil`	No
`nachricht`	Yes
`mit_quelle`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.11.2Nov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it states that nothing is sent, that the output is files handed to a mail program, that the verification report from `verify --email` is always included, and that the default temp directory persists so the returned path stays valid. Missing are error conditions and any permission/auth notes.

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?

Structure is strong: a one-line purpose, an aligned parameter glossary, then a bolded behavioral caveat. Some sentences are padded (ADR cross-references, "dieselbe Zusage wie beim Brief"), but the front-loading and formatting make the content scannable.

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?

No output schema and no annotations exist, and the description covers inputs plus the critical non-obvious behavior (no sending, files produced, verification report attached). It implies a returned path but does not fully describe the response shape or failure modes, which is the remaining gap.

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?

Schema description coverage is 0%, yet all five parameters are explained with meaning and defaults: `nachricht` is markdown text with frontmatter (not a path) requiring `typ: email`; `profil` falls back to the frontmatter value; `als` takes "pfad" or "base64"; `ziel` defaults to a persisting temp dir; `mit_quelle` discloses content otherwise invisible in the letter. This fully compensates for the empty 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?

The opening line gives a specific verb and resource: it renders ("Setzt") the email version and verifies it ("misst sie nach"). The "E-Mail" vs. the sibling `brief_rendern`'s letter framing makes the distinction inferable, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the required `typ: email` frontmatter tells the agent what input qualifies, and "Es wird nichts versendet" scopes the tool's role versus a mail program. There is no explicit when-to-use/when-not framing and no comparison to `brief_rendern` or `brief_pruefen`.

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

Deploy Server