Skip to main content
Glama
Sign In

FrankKi

by app.frankki
OverviewDiscussionsAdmin

Absender und Briefpapier von der Website einrichten

brand_setup_from_website
Destructive

Firmenwebsite zu Absender, Marke und Briefpapier in zwei Aufrufen. apply false liest die Website und liefert einen Vorschlag: Logo, Farben, Schrift, Absenderprofil mit Pflichtangaben aus dem Impressum, Absenderadresse und ein passendes Briefpapier, dazu die fehlenden Pflichtangaben, die eine Frage an die Person und Seite 1 dieses Briefpapiers als Bild (letterheadPreview). apply true speichert alles auf einmal mit der proposalId daraus und brandingOwnershipConfirmed true: Marke, Absenderprofil, Absenderadresse, Briefpapier mit Logo als Standard, und zeigt eine Vorschau als Bild. Bestehende Angaben der Person bleiben erhalten, senderOverrides gehen vor. Nächster Schritt: template_clone_from_library. Technischer Tool-Name: brand_setup_from_website. EN: Company website to sender, brand and letterhead in two calls. apply false reads the website and returns a proposal: logo, colours, typeface, sender profile with mandatory details from the imprint, sender address and a matching letterhead, plus the missing details, the one question for the person and page 1 of that letterhead as an image (letterheadPreview). apply true saves everything at once with its proposalId and brandingOwnershipConfirmed true: brand, sender profile, sender address, letterhead with logo as default, and shows a preview image. Details the person already has on file stay, senderOverrides take precedence. Next step: template_clone_from_library. Technical tool name: brand_setup_from_website.

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": {
      "websiteUrl": "<websiteUrl>"
    },
    "name": "brand_setup_from_website"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNofalse liefert den Vorschlag, true speichert ihn. EN: false returns the proposal, true saves it.
proposalNoDas proposal aus der Antwort mit apply false, gern von der Person korrigiert. Spart den zweiten Website-Abruf. EN: The proposal from the apply false answer, optionally corrected by the person. Saves a second website read.
reasoningNo
proposalIdNoBei apply true erforderlich: die proposalId aus der Antwort mit apply false, 30 Minuten gültig. EN: Required with apply true: the proposalId from the apply false answer, valid for 30 minutes.
websiteUrlYesÖffentliche Firmenwebsite, z.B. https://beispiel.de. EN: Public company website.
designPresetIdNoBriefpapier-Vorlage aus letter_design_list_presets. Standard ist der Vorschlag. EN: Letterhead preset from letter_design_list_presets. Defaults to the recommendation.
senderOverridesNoKorrekturen und fehlende Angaben von der Person, sie gehen allem anderen vor. EN: Corrections and missing details from the person; they take precedence.
brandingOwnershipConfirmedNoBei apply true erforderlich: die Person bestätigt, dass sie Logo und Marke verwenden darf. EN: Required with apply true: the person confirms they may use the logo and brand.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / brandingOwnershipConfirmed / description
      Previous value: -"Pflicht bei apply true: die Person bestätigt, dass sie Logo und Marke verwenden darf. EN: Required with apply true: the person confirms they may use the logo and brand."New value: +"Bei apply true erforderlich: die Person bestätigt, dass sie Logo und Marke verwenden darf. EN: Required with apply true: the person confirms they may use the logo and brand."
    • changedInput schema / properties / proposalId / description
      Previous value: -"Pflicht bei apply true: die proposalId aus der Antwort mit apply false, 30 Minuten gültig. EN: Required with apply true: the proposalId from the apply false answer, valid for 30 minutes."New value: +"Bei apply true erforderlich: die proposalId aus der Antwort mit apply false, 30 Minuten gültig. EN: Required with apply true: the proposalId from the apply false answer, valid for 30 minutes."
  2. Changed3 schema fields changed
    • addedInput schema / properties / proposal / properties / sender / properties / bankverbindung
      Added value: +{
+  "additionalProperties": false,
+  "description": "Konto für Rechnungen und Zahlungserinnerungen. EN: Account for invoices and payment reminders.",
+  "properties": {
+    "bankname": {
+      "type": "string"
+    },
+    "bic": {
+      "type": "string"
+    },
+    "iban": {
+      "type": "string"
+    }
+  },
+  "type": [
+    "object",
+    "null"
+  ]
+}
    • addedInput schema / properties / proposalId
      Added value: +{
+  "description": "Pflicht bei apply true: die proposalId aus der Antwort mit apply false, 30 Minuten gültig. EN: Required with apply true: the proposalId from the apply false answer, valid for 30 minutes.",
+  "type": "string"
+}
    • addedInput schema / properties / senderOverrides / properties / bankverbindung
      Added value: +{
+  "additionalProperties": false,
+  "description": "Konto für Rechnungen und Zahlungserinnerungen. EN: Account for invoices and payment reminders.",
+  "properties": {
+    "bankname": {
+      "type": "string"
+    },
+    "bic": {
+      "type": "string"
+    },
+    "iban": {
+      "type": "string"
+    }
+  },
+  "type": [
+    "object",
+    "null"
+  ]
+}
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

Despite annotations already flagging destructiveHint=true, the description adds real context: existing details on file are preserved, senderOverrides take precedence, proposalId expires after 30 minutes, and the generated letterhead becomes the default. It stops short of saying what an apply=true call may overwrite (e.g. a previously set default letterhead), which is the main residual risk for a destructive write.

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?

Content is front-loaded with the two-call behavior, which is good, but the entire text is duplicated verbatim in German and English, roughly doubling length for no informational gain. The technical tool name is also repeated at the end, adding nothing.

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?

For an 8-parameter destructive tool with no output schema, the description substitutes well by enumerating what apply=false returns (logo, colours, typeface, sender profile, imprint data, letterheadPreview image) and what apply=true persists plus a preview image. Failure modes (unreachable site, invalid URL, expired proposalId) are left unaddressed.

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?

With 88% schema coverage the baseline is 3; the description goes beyond it by explaining proposalId's 30-minute validity and apply=true requirement, the ownership confirmation gate, the precedence of senderOverrides, and that the proposal object saves a second website fetch. Remaining parameters (reasoning, designPresetId default) are covered only in 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 ('reads the website and returns a proposal' of sender, brand, letterhead) and the two-call mechanism. It names the follow-on tool (template_clone_from_library) but never distinguishes itself from the close sibling brand_import_from_website or brand_kit_save, so an agent cannot rule those out from the text alone.

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?

The apply=false vs apply=true split is spelled out explicitly, as are the preconditions for the save branch (proposalId from the first call, brandingOwnershipConfirmed=true) and the reuse of the proposal to avoid a second website read. What is missing is any statement of when to prefer a sibling (brand_import_from_website, letterhead_upload) instead.

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

All FrankKi toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources