claude-interview-mode

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

4/4 tools missing one or more hints — start_interview (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); record (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_context (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +1 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — end_interview overwrites at line 240 (sb)

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — end_interview (line 206: sb.from("interview_metadata").insert({)

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

Only 1/4 tool handlers declare input schemas (25%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 1/4 tool handlers wrap calls in try/catch (25%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Tool description accuracy

end_interview: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.