Skip to main content
Glama

Abweichung zur Vorlage prüfen

template_diff_check
Read-only

Vergleicht einen fertigen Brief mit seiner Vorlage und zeigt, wo er abweicht. Eine Blockvorlage vergleicht finalBlocks an Stelle von finalContent, Text für Text in Lesereihenfolge. Kostenlos und rein lesend. EN: Compares a finished letter with its template and shows where it deviates. A block template compares finalBlocks in place of finalContent, text by text in reading order. Free and read-only.

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": {
      "templateId": "<templateId>",
      "finalSubject": "<finalSubject>"
    },
    "name": "template_diff_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasoningNo
versionIdNoOptional: bestimmte Version, sonst die freigegebene. EN: Optional: a specific version, otherwise the released one.
templateIdYesId der Vorlage aus template_list / template_get. EN: The template ID from template_list / template_get.
finalBlocksNoDie finalen Blöcke, wenn der Brief strukturiert ist. Verglichen werden die Texte in Lesereihenfolge. EN: The final blocks when the letter is structured. The texts are compared in reading order.
mergeFieldsNoZuordnung der Platzhalter-Namen zu Werten, z. B. { "provider": "Telekom" }. EN: Mapping of placeholder names to values, e.g. { "provider": "Telekom" }.
finalContentNoDer finale Brieftext. Ein Blockbrief kommt als finalBlocks. EN: The final letter text. A block letter comes as finalBlocks.
finalSubjectYesDer finale Betreff des Briefs. EN: The letter's final subject line.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / finalBlocks / description
      Previous value: -"Deine finalen Blöcke, wenn der Brief strukturiert ist. Verglichen werden die Texte in Lesereihenfolge. EN: Your final blocks when the letter is structured. The texts are compared in reading order."New value: +"Die finalen Blöcke, wenn der Brief strukturiert ist. Verglichen werden die Texte in Lesereihenfolge. EN: The final blocks when the letter is structured. The texts are compared in reading order."
    • changedInput schema / properties / finalContent / description
      Previous value: -"Dein finaler Brieftext. Bei einem Blockbrief stattdessen finalBlocks. EN: Your final letter text. For a block letter use finalBlocks instead."New value: +"Der finale Brieftext. Ein Blockbrief kommt als finalBlocks. EN: The final letter text. A block letter comes as finalBlocks."
    • changedInput schema / properties / finalSubject / description
      Previous value: -"Dein finaler Betreff. EN: Your final subject line."New value: +"Der finale Betreff des Briefs. EN: The letter's final subject line."
  2. Changed1 schema field changed
    • changedInput schema / properties / finalBlocks / description
      Previous value: -"Deine finalen Bloecke, wenn der Brief strukturiert ist. Verglichen werden die Texte in Lesereihenfolge. EN: Your final blocks when the letter is structured. The texts are compared in reading order."New value: +"Deine finalen Blöcke, wenn der Brief strukturiert ist. Verglichen werden die Texte in Lesereihenfolge. EN: Your final blocks when the letter is structured. The texts are compared in reading order."
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Beyond annotations (readOnly=true, destructive=false, openWorld=false), it adds the cost signal 'Kostenlos'/'free' and, more importantly, describes the comparison mechanics: blocks are compared text-by-text in reading order instead of raw content. That is real behavioral disclosure an agent would not get from annotations. It does not explain the shape of the deviation report, which keeps it below 5.

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 core purpose and the block/template variant rule before the read-only note. The German and English sentences are semantically identical, which doubles length, but this is a deliberate bilingual convention rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, a nested object and no output schema, the description covers the main content-parameter decision but never says what the deviation result looks like (it 'shows where it deviates' — a list? per-block flags?). It also says nothing about failure modes such as an unknown templateId or a missing released version.

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 already 86%, so baseline is 3, but the description adds cross-parameter logic not present in any single schema entry: a block template compares finalBlocks instead of finalContent. That resolves the ambiguity of which of the two mutually exclusive content parameters to supply.

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: compares a finished letter against its template and reports deviations. It is clearly distinguishable from siblings like template_get (retrieve) and template_apply_with_merge_fields (apply), because it is the only read-only comparison tool in the list.

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: an agent can infer this is the tool for verifying a letter still matches its template, and the block-vs-text sentence implicitly routes the choice between finalBlocks and finalContent. However, no explicit when-to-use/when-not guidance or named alternative (e.g. template_get) is given.

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.