Three tools with minimal parameter descriptions and no output schemas. Tool names follow verb_noun convention (check_*, get_*), which is good. However, descriptions are generic (34-72 chars, below the 194-char baseline), and critically, NO parameter descriptions exist for 'name' in check_person_report. Input schemas are present but lack descriptions. No error handling guidance, no recovery paths, and no documentation of what fields are returned. The server reads from Google Sheets but exposes no validation, rate limiting, or permission gates. Resources and prompts are defined but lack depth.
Check who hasn't submitted their weekly reports yet
Check if a specific person has submitted their weekly report
Get statistics about weekly report submissions
Parameter 'name' in check_person_report has no description. LLM cannot infer whether to pass a full name, username, or ID.
No output schemas documented. Tools return plain strings; LLM cannot parse structured data or chain results to downstream tools.
Tool descriptions are 34 - 72 characters (well below 194-char baseline). Lack context on WHEN to use each tool and what distinguishes them.
No error handling or recovery guidance. If a name is not found or Google Sheets is unreachable, the LLM receives a plain error with no actionable next step.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
Google Sheets credentials (service_account.json) hardcoded in file path. No secret injection pattern; credentials could leak if logs are exposed.