Redis server has 4 tools with complete input schemas and descriptions. Naming follows verb_noun convention (set, get, delete, list). Descriptions are present but brief (10-40 chars), below the 50-200 char LLM-optimized baseline. Parameter descriptions are minimal. No output schemas documented. Error handling is basic, no recovery guidance or categorization. Missing tool annotations (readOnlyHint, destructiveHint). The 'delete' tool accepts both string and array but lacks clear guidance on behavior differences. No pagination support for 'list' despite pattern matching potentially returning large result sets.
Delete one or more keys from Redis
Get value by key from Redis
List Redis keys matching a pattern
Set a Redis key-value pair with optional expiration
Tool descriptions are too brief (10-40 chars). LLM-optimized descriptions should be 50-200 chars and explain WHAT the tool does, WHEN to use it, and any prerequisites. Current descriptions lack context for tool selection.
No output schemas documented. LLMs need to know what fields to expect in responses to plan downstream calls and extract data correctly. Currently only text responses are returned without structured field definitions.
Missing tool annotations. 'set' and 'delete' are write/destructive operations but lack destructiveHint annotation. 'get' and 'list' are read-only but lack readOnlyHint. These hints guide agent planning and safety checks.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | <=2025-11-25 | v2 |
'list' tool lacks pagination support. Pattern matching can return large result sets that blow context windows. Should accept limit and offset/cursor parameters and return total count.
Error handling provides no recovery guidance. Errors return plain text without categorization (retryable vs user-fixable vs fatal). No actionable next steps for the agent when operations fail.