Loading ToolBench

Reading the current corpus…

doopl MCP server · D · ToolBench

doopl

Model Context Protocol (MCP) server that exposes DeepL translation capabilities to Claude, Claude Desktop, and other MCP-compatible AI clients

2026-07-28+STDIO3 tools

50/100

Definition Quality57

Protocol Readiness50

Supportability38

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence

Current-spec patterns detected

Summary

Three tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Tool names are action-oriented (translate, languages, usage) but descriptions lack depth on when/why to use each tool. The 'languages' tool has an enum constraint on 'resource' parameter, which is good, but 'translate' lacks formality enum validation guidance in description. No output schemas documented for any tool. Error handling and recovery guidance absent.

Tools (3)

languagesread onlyauthsource verified60/100

List supported languages for a given resource type

translateread onlyauthsource verified63/100

Translate text to a target language using DeepL API

usageread onlyauthsource verified47/100

Check API quota and usage for your DeepL account

Issues (5)

CRITICALtool ↗

No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields without knowing response structure.

translatelanguagesusage

HIGHtool-description ↗

'usage' tool has empty input schema (no properties defined). Description is only 35 chars ('Check API quota and usage for your DeepL account'), insufficient for LLM selection.

usage

HIGHtool-description ↗

'translate' description lacks guidance on when to use formality parameter or how glossary_id affects output. Missing dependency hints for multi-step workflows.

translate

MEDIUMtool-description ↗

'languages' description (47 chars) is too brief. Does not explain what structure is returned or when to call it relative to translate.

languages

HIGHrecovery-guide ↗

Recommendations

Document output schema for each tool. E.g., 'translate returns {translated_text: string, detected_source_language: string, character_count: number}'.
Expand 'usage' description to 100+ chars: 'Returns your DeepL API quota (character limit, documents limit) and current usage. Call this before translate to check remaining capacity.'
Add parameter descriptions for 'translate': explain formality enum values (default=neutral, more=formal, less=casual), when glossary_id is useful, and what happens if source_lang is omitted.
Expand 'languages' description: 'Returns list of supported language codes for the specified resource type. Call this first to validate target_lang before translate.'
Add error recovery guidance: 'If translate fails with invalid language code, call languages to see supported codes. If quota exceeded, call usage to check limits.'

Score history

Overall score trend

First recorded score · v2 rubric

50/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	50	2026-07-28+	v2