Loading ToolBench
Rooms by I-Ops — local, inspectable shared rooms for agent sessions
iops-rooms has 6 tools with basic naming and descriptions, but significant gaps in schema completeness and parameter documentation. Tool names follow verb_noun convention (post_note, share_diff, request_review, approve, get_room_status, list_events), which is good. However, descriptions are minimal (10-50 chars), parameter schemas lack detail, and output schemas are not documented. No error handling guidance, no input validation hints, and no security considerations visible. The server is STDIO-only, which is a hard transport limitation.
Approve work in the room
Get the current status of the room
List events in the room
Post a note to the room board
Request a review from other room participants
Share a diff of file changes to the room
Output schemas not documented. No tool returns a documented schema showing what fields the LLM should expect. This forces LLMs to guess at response structure and breaks downstream tool chaining.
Descriptions are too brief (10-50 chars). Rubric baseline is 194 chars average. Descriptions lack WHAT the tool does, WHEN to use it, and any prerequisites. Example: 'Post a note to the room board' does not explain when to use this vs other communication tools.
Parameter descriptions are minimal or missing context. 'text' in post_note has a description, but 'limit' in list_events lacks guidance on valid range (1-100? 1-1000?). No constraints documented.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |
No error handling guidance. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next. A failed approval or diff share leaves the agent without recovery direction.
No pagination or result limits documented for list_events. If a room has thousands of events, returning all of them will blow the context window. No guidance on max results or cursor-based pagination.