Skip to main content
Glama

FrankKi

by app.frankki

Abweichung zur Vorlage prüfen

template_diff_check
Read-only

Vergleicht deinen finalen Brief mit der Vorlage und zeigt dir, wo du abgewichen bist. Bei einer Blockvorlage uebergibst du finalBlocks statt finalContent; verglichen werden die Texte in Lesereihenfolge. Kostenlos und rein lesend. EN: Compares your final letter with the template and shows you where you deviated. For a block template pass finalBlocks instead of finalContent; the texts are compared in reading order. Free and read-only.

Input Schema

TableJSON 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.
finalBlocksNoDeine 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.
mergeFieldsNoZuordnung der Platzhalter-Namen zu Werten, z. B. { "provider": "Telekom" }. EN: Mapping of placeholder names to values, e.g. { "provider": "Telekom" }.
finalContentNoDein finaler Brieftext. Bei einem Blockbrief stattdessen finalBlocks. EN: Your final letter text. For a block letter use finalBlocks instead.
finalSubjectYesDein finaler Betreff. EN: Your final subject line.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

The description explicitly states 'rein lesend' / 'read-only' and 'free', reinforcing the readOnlyHint=true annotation. It adds behavioral detail that the text comparison happens in reading order, but it does not describe the shape of the deviation output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, front-loaded with the purpose, and each clause adds either the block-template rule or the read-only/free status. The bilingual repetition is compact and not excessive.

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 a read-only comparison tool with detailed schema descriptions, the main facts are covered: what is compared, the block-vs-content input distinction, and safety/cost. A minor gap is the lack of an output format since no output schema is provided, but the description still gives enough to invoke the tool correctly.

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 coverage is 86%, so the schema already documents most parameters. The description's finalBlocks/finalContent guidance largely repeats the schema's existing descriptions and adds little new meaning beyond emphasizing the block-template case.

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?

The description states a specific verb ('compares'), a resource ('your final letter' vs 'the template'), and the result ('shows you where you deviated'). This clearly differentiates it from siblings such as template_apply_with_merge_fields or template_preview.

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?

It gives clear context: use it to compare a finished letter against a template and see deviations. It also gives parameter-level guidance (pass finalBlocks for a block template, finalContent otherwise), though it does not explicitly name alternative tools or exclusion criteria.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0
Disambiguation2/5

The surface contains multiple clusters whose boundaries are unclear: letterhead_list/letter_design_list/brand_kit_get/profile_get all expose similar letterhead/brand data, and letter_preview/template_preview/letter_design_preview are easy to confuse. The many *_app variants (approval_decide_app, template_decide_app, status/page-url helpers) further duplicate core actions. Rich descriptions help, but with 72 tools an agent will frequently pick the wrong member of a cluster.

Naming Consistency3/5

Most tools follow a readable snake_case resource_action pattern (address_upsert, approval_list, letter_schedule, wallet_balance). However, there are notable exceptions like analytics_summary, mcp_health, pricing_tiers, shipping_quote and order_einlieferungsbeleg, plus German/English mixing and semantically competing prefixes (letterhead_ vs letter_design_ vs brand_kit_). The style is not chaotic, but it is not uniformly consistent.

Tool Count1/5

With 72 tools this is an extreme mismatch for an MCP surface. The count is inflated by app-card-only helpers, separate preview variants and overlapping design/letterhead/brand tools that could be consolidated. Even a complex domain like postal letters does not justify this many top-level entry points.

Completeness4/5

The core domain is very well covered: addresses, letters, documents, templates, approvals, sender profiles, wallet, scheduling, archive exports and analytics all have lifecycle operations. The main gaps are minor workarounds rather than dead ends: no delete for addresses or documents, no attachment listing/deletion, and letter corrections are handled by creating a new draft.

Resources