Loading ToolBench
Connect Canvas and other school platforms to AI agents — MCP server, JSON CLI, agent skill (Hermes/OpenClaw), and event watcher for assignments, grades, and announcements.
schoolbridge has 8 well-named, read-only tools with clear descriptions (avg 156 chars, within baseline 194). All tools start with action verbs (list_, get_, check_). Input schemas are present and typed for all tools. However, parameter descriptions are sparse or missing in several tools (e.g., list_upcoming_work 'days' param lacks min/max guidance in description text), and output schemas are not documented in the source. Error handling and recovery guidance are absent. No tool annotations (readOnlyHint, etc.) despite all being read-only. The 'priority' field in list_upcoming_work is mentioned but not formally documented as part of the output schema.
Compare the LMS with the last check and return everything that changed since: new assignments, due-date changes, newly posted or changed grades, new announcements, new discussions, new/moved calendar events, newly published course content and files, new teacher feedback on submissions, and course-grade moves. Persists the new state, so each call reports only fresh changes. The first call ever returns baseline=true with no events.
Full details for one assignment, including its description/instructions as plain text. Use this before building a study plan or estimating effort.
Current overall grade per course plus every assignment graded in the last two weeks (with scores).
Teacher announcements across all courses from the last N days (default 14), newest first.
Course calendar events for the next N days (default 30): review sessions, field trips, in-class tests, and other scheduled happenings that aren't assignments.
Output schemas not documented. Tool descriptions mention what is returned (e.g., 'priority hint', 'baseline=true') but formal output schema is not visible in source. LLMs cannot plan downstream operations without knowing response structure.
Parameter descriptions lack constraint details. 'days' parameter in list_upcoming_work, list_announcements, list_recent_feedback has min/max in schema but description text does not explain the range or rationale.
No tool annotations despite all tools being read-only. MCP spec supports readOnlyHint to signal safe tools. This helps agents reason about retry safety and side effects.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 60 | 2026-07-28+ | v2 |
List the student's active courses with the current grade and score for each.
Teacher comments left on the student's submitted work in the last N days (default 14) — useful for 'what did my teacher say about…' and for improving future work.
Assignments, quizzes, and tests due in the next N days (default 7) across all courses, plus recent overdue unsubmitted work. Each item carries a 0–100 `priority` hint that weighs due date, point value, test-likeness, and missing status — use it as a starting point for ranking, but override it with judgment (e.g. start long essays earlier than their due date suggests).
No error handling or recovery guidance. Tools do not document what errors can occur (e.g., invalid course_id, network failure, auth failure) or how to recover.
Pagination not documented for list tools. list_courses, list_upcoming_work, list_announcements, list_calendar_events, list_recent_feedback do not mention pagination, limits, or how many results are returned.