Fast grep with AI-native output. Token-compressed results for LLM coding agents.
rustygrep exposes 3 well-named search tools with complete input schemas and reasonable descriptions. All tools follow verb_noun naming (rustygrep_search, rustygrep_files, rustygrep_count). Schemas include proper types, enums, and defaults. However, descriptions are brief (34 - 72 chars), below the 50 - 200 char LLM-optimized baseline. Parameter descriptions are minimal or absent for some fields (e.g., 'type' lacks detail on valid values). Output schemas are not documented, LLMs cannot predict response structure. Error handling is present but not recovery-focused. No tool annotations (readOnlyHint, idempotentHint) despite all being read-only operations.
Count matches per file for a pattern.
List files containing a pattern (no line content). Fast file discovery.
Search for a regex pattern in files. Returns matching lines with file paths and line numbers.
Output schemas not documented. LLMs cannot predict response structure (fields, types, pagination). Forces trial-and-error parsing.
Descriptions are 34 - 72 chars, below LLM-optimized baseline (50 - 200 chars). Lack context on WHEN to use each tool and what distinguishes them.
Parameter 'type' lacks description detail. Should explain valid values (e.g., 'File extension without dot: rs, py, js, ts, etc.').
No tool annotations despite all tools being read-only and idempotent. Missing readOnlyHint and idempotentHint metadata.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Error handling present but not recovery-focused. No guidance on what to do if pattern is invalid or path not found.