Loading ToolBench
Local read-only repository context retrieval for AI coding agents.
Single tool 'repo_context' has a basic description but critically lacks a complete input schema. The description 'Retrieve repository context for AI coding agents' is only 50 chars (below the 194-char baseline for A+ tools). Input schema shows only a 'q' parameter with type 'string' and minimal description 'Query string for repository context retrieval' (48 chars). No output schema is documented. No error handling guidance, no parameter constraints (enums, ranges, patterns), and no indication of what fields the response contains. The tool name 'repo_context' is a noun phrase rather than a verb_noun pattern (should be 'get_repo_context' or 'retrieve_repo_context'). No pagination, no result limits documented, no guidance on query syntax or expected behavior.
Retrieve repository context for AI coding agents
Tool name 'repo_context' is a noun phrase, not a verb_noun action. Should be 'get_repo_context' or 'retrieve_repo_context' to signal the action to LLMs.
Input schema is incomplete. Only 'q' parameter defined with minimal description (48 chars). No constraints (enum, pattern, minLength, maxLength), no examples of valid queries, no guidance on query syntax or special operators.
No output schema documented. LLMs cannot plan downstream operations or extract fields without knowing response structure. Must document return type, field names, and types.
Tool description is only 50 characters (below 194-char baseline). Lacks WHEN to use it, WHAT it returns, and HOW to construct queries. Too brief for LLM selection.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 32 | 2026-07-28+ | v2 |
No error handling guidance. No documentation of failure modes (invalid query, repo not found, timeout). LLMs cannot recover from errors without explicit recovery hints.