MCP Developer Server

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

60/60 tools missing one or more hints — get_server_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); health_check (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); playwright_launch_browser (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +57 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.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — get_gpu_status (line 58: result = subprocess.run()

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

Tool inputs are validated

45/60 tool handlers declare input schemas (75%)

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

Tool handlers catch errors

49/60 tool handlers wrap calls in try/catch (82%)

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

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

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