Loading ToolBench
Collection of three MCP servers: Bitwarden/Vaultwarden vault management, TMDB movie/TV database search and details, and OpenWeatherMap weather data
33 tools across 4 domains (TMDB, weather, Bitwarden). All tools have descriptions (10-200 chars, mostly adequate). Input schemas present with typed parameters and descriptions. However, output schemas are NOT documented, critical gap per pattern:tool. Parameter descriptions are generic (e.g., 'TMDB movie ID' repeated 20+ times). No error handling guidance. No tool annotations (readOnlyHint/destructiveHint). Bitwarden tools expose sensitive operations (create/update/delete cipher) without confirmation patterns. TMDB tools are well-structured but lack output schema documentation. Weather tool has minimal parameter descriptions.
Create a new vault item (cipher) in Bitwarden/Vaultwarden. Supports login items with username/password, notes, custom fields, and folder assignment.
Delete a vault item (cipher) from Bitwarden/Vaultwarden. Permanently removes the item from the vault.
Discover movies with advanced filtering options including genres, ratings, release year, and more.
Discover TV series with advanced filtering options including genres, ratings, air date, networks, and more.
Get the list of official genres for movies or TV series.
Get a specific vault item (cipher) by ID from Bitwarden/Vaultwarden. Returns full details including login credentials, notes, custom fields, and attachments.
Output schemas not documented. LLMs cannot plan downstream tool calls or extract required fields without knowing response structure. Critical for tool chaining.
Destructive operations (create_cipher, update_cipher, delete_cipher) lack confirmation/dry-run patterns. Agents can permanently delete vault items without user approval.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). LLMs cannot distinguish safe reads from destructive writes without explicit hints.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
Get current weather from OpenWeatherMap. Returns temp, feels_like, humidity, pressure, wind, conditions, and description in Spanish. Use mode='forecast' for 5-day forecast (3-hour intervals).
List all vault items (ciphers) from Bitwarden/Vaultwarden. Returns login credentials, notes, custom fields, and metadata for each item.
Get the cast and crew for a movie by TMDB ID.
Get detailed movie information by TMDB ID. Includes budget, revenue, runtime, genres, production companies, collections, and more.
Get movie recommendations based on a known movie ID. Uses TMDB's recommendation engine.
Get user reviews for a movie by TMDB ID.
Get similar movies based on a known movie ID.
Get videos (trailers, teasers, clips) for a movie by TMDB ID.
Get detailed information about a person by TMDB ID. Includes biography, birth/death dates, known for titles, and more.
Get all movie credits for a person by TMDB ID.
Get all TV credits for a person by TMDB ID.
Search for movies by title. Returns paginated results with overview, rating, release date, poster path, and genre IDs.
Search across movies, TV series, and people. Returns paginated results with mixed media types.
Search for people (actors, directors, etc.) by name. Returns paginated results with known for titles and profile images.
Search for TV series by title. Returns paginated results with overview, rating, first air date, poster path, and genre IDs.
Get trending movies, TV series, or all media for a specified time window (day or week).
Get trending movies for a specified time window (day or week).
Get trending TV series for a specified time window (day or week).
Get the cast and crew for a TV series by TMDB ID.
Get detailed TV series information by TMDB ID. Includes number of seasons, episodes, networks, production companies, and more.
Get detailed information about a specific TV episode by series ID, season number, and episode number.
Get TV series recommendations based on a known series ID. Uses TMDB's recommendation engine.
Get user reviews for a TV series by TMDB ID.
Get detailed information about a specific TV season by series ID and season number.
Get similar TV series based on a known series ID.
Get videos (trailers, teasers, clips) for a TV series by TMDB ID.
Update an existing vault item (cipher) in Bitwarden/Vaultwarden. Can modify name, notes, login credentials, custom fields, and folder assignment.
Parameter descriptions are generic and repetitive (e.g., 'TMDB movie ID' appears 20+ times). LLMs benefit from context-specific guidance on when to use each tool.
No error handling guidance. Tools return errors but do not tell LLMs what to do next (retry, ask user, try alternative tool).