Loading ToolBench

Reading the current corpus…

slims-mcp MCP server · D · ToolBench

slims-mcp

MCP server for querying a SLiMS (Senayan Library Management System) library database. Provides tools for searching books, checking availability, retrieving statistics, and discovering popular subjects.

<=2025-11-25STDIO6 tools

55/100

Definition Quality69

Protocol Readiness47

Supportability36

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

Server defines 6 tools with complete schemas and descriptions in Indonesian. All tools are READ_ONLY and properly registered via mcp-go framework. Naming follows verb_noun pattern (search_*, get_*, check_*). Descriptions are present (avg ~80 chars) but lack actionable context for LLM selection. Parameters have types and descriptions, but lack constraints (enums, ranges, format specs). No output schemas documented. Error handling not visible in provided code. Missing idempotent/readonly hints despite all tools being safe.

Tools (6)

check_book_availabilityread onlysource verified75/100

Memeriksa status ketersediaan buku berdasarkan ID bibliografi

get_popular_subjectsread onlysource verified68/100

Mendapatkan daftar subjek/topik paling populer

get_total_booksread onlysource verified63/100

Mendapatkan jumlah total buku dan eksemplar

search_booksread onlysource verified73/100

Mencari buku berdasarkan judul, pengarang, atau subjek dengan dukungan paginasi

search_latest_booksread onlysource verified68/100

Mendapatkan daftar buku terbaru

search_popular_booksread onlysource verified68/100

Mendapatkan daftar buku paling populer berdasarkan riwayat peminjaman

Issues (5)

HIGHtool ↗

No output schemas documented. LLMs cannot predict response structure or plan downstream calls. Tools return unstructured data requiring parsing.

search_bookssearch_latest_bookssearch_popular_bookscheck_book_availabilityget_total_booksget_popular_subjects

HIGHconstrained-input ↗

Numeric parameters (limit, page, biblio_id) lack constraints. No min/max bounds specified. LLMs can pass invalid values (negative page, limit > 50 despite description saying 'maks: 50').

search_bookssearch_latest_bookssearch_popular_booksget_popular_subjects

MEDIUMtool-description ↗

Descriptions lack actionable context. No guidance on WHEN to use each tool vs alternatives. 'Mendapatkan daftar buku terbaru' does not explain when to call this vs search_books with year filter.

search_latest_bookssearch_popular_booksget_popular_subjects

Recommendations

Document output schemas for all tools. Example for search_books: {books: [{biblio_id: number, title: string, author: string, year: number, available_count: number}], total: number, page: number}
Add numeric constraints to schema. Use mcp.WithNumber('limit', mcp.Min(1), mcp.Max(50)) to enforce bounds at registration time.
Enhance descriptions with selection context. E.g., 'Get latest books added to the library. Use this to show recent acquisitions; use search_books for keyword-based discovery.'
Add tool annotations via mcp.WithReadOnly() or equivalent to signal safety to LLMs and enable aggressive retry strategies.
Implement and document error handling: return structured errors with recovery hints (e.g., 'No books found. Try broadening the search query or removing year filter.').

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

55/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	55	<=2025-11-25	v2